I
nte
rna
t
io
na
l J
o
urna
l o
f
Rec
o
nfig
ura
ble a
nd
E
m
be
dd
e
d Sy
s
t
e
m
s
(
I
J
R
E
S)
Vo
l.
14
,
No
.
2
,
J
u
ly
20
25
,
p
p
.
497
~
5
0
6
I
SS
N:
2089
-
4864
,
DOI
:
1
0
.
1
1
5
9
1
/i
j
r
es
.
v
1
4
.
i
2
.
pp
4
9
7
-
506
497
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
r
es.ia
esco
r
e.
co
m
Inv
estig
a
ting the
perfor
m
a
nce of
R
NN
m
o
del
to fore
ca
st t
he
elect
rici
ty po
w
er c
o
nsu
m
p
tion in
G
ua
ng
z
ho
u C
hina
H
a
n
M
ing
y
ing
1
,
Az
m
a
n Ab
M
a
lik
1
,
No
o
r
m
a
din
a
h Al
lia
s
2
,
I
rni H
a
m
iza
H
a
m
za
h
3
1
S
c
h
o
o
l
o
f
C
o
mp
u
t
e
r
S
c
i
e
n
c
e
,
U
n
i
v
e
r
si
t
i
S
a
i
n
s
M
a
l
a
y
si
a
,
P
u
l
a
u
P
i
n
a
n
g
,
M
a
l
a
y
si
a
2
S
c
h
o
o
l
o
f
C
o
mp
u
t
i
n
g
S
c
i
e
n
c
e
s,
C
o
l
l
e
g
e
o
f
C
o
mp
u
t
i
n
g
,
I
n
f
o
r
mat
i
c
s a
n
d
M
a
t
h
e
ma
t
i
c
s,
A
l
-
K
h
a
w
a
r
i
z
mi
B
u
i
l
d
i
n
g
,
U
n
i
v
e
r
si
t
i
T
e
k
n
o
l
o
g
i
M
A
R
A
,
S
h
a
h
A
l
a
m,
M
a
l
a
y
si
a
3
El
e
c
t
r
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
S
t
u
d
i
e
s,
U
n
i
v
e
r
si
t
i
T
e
k
n
o
l
o
g
i
M
A
R
A
,
P
u
l
a
u
P
i
n
a
n
g
,
M
a
l
a
y
si
a
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
A
p
r
4
,
2
0
2
4
R
ev
i
s
ed
Ma
y
9
,
2
0
2
5
A
cc
ep
ted
J
u
n
1
0
,
2
0
2
5
T
h
e
p
ro
jec
t
in
it
iativ
e
s
to
c
re
a
te
a
re
li
a
b
le
p
re
d
icti
o
n
m
o
d
e
l
f
o
r
p
o
w
e
r
lo
a
d
s
in
G
u
a
n
g
z
h
o
u
,
Ch
in
a
.
T
h
e
p
o
w
e
r
in
d
u
stry
is
fa
c
in
g
issu
e
s
d
u
e
to
ra
p
id
m
a
rk
e
t
g
ro
w
th
a
n
d
th
e
n
e
c
e
ss
it
y
f
o
r
b
e
tt
e
r
g
rid
m
a
n
a
g
e
m
e
n
t,
p
ro
m
p
ti
n
g
th
is
re
sp
o
n
se
.
In
d
e
v
e
lo
p
i
n
g
th
e
m
o
d
e
l
s,
c
o
n
v
e
n
ti
o
n
a
l
m
a
c
h
in
e
lea
rn
in
g
m
o
d
e
ls
h
a
v
e
b
e
e
n
u
se
d
s
o
f
a
r,
b
u
t
i
n
t
h
is
stu
d
y
,
th
e
p
e
rf
o
rm
a
n
c
e
o
f
d
e
e
p
l
e
a
rn
in
g
is
in
v
e
stig
a
ted
.
T
h
e
re
f
o
re
,
th
e
re
c
u
rre
n
t
n
e
u
ra
l
n
e
tw
o
rk
(RNN
)
wa
s se
lec
ted
f
o
r
th
e
p
re
d
icti
o
n
o
f
e
lec
tri
c
it
y
c
o
n
su
m
p
ti
o
n
.
L
a
ter,
th
e
p
e
rf
o
rm
a
n
c
e
o
f
th
e
m
o
d
e
l
w
a
s
c
o
m
p
a
re
d
w
it
h
a
u
to
re
g
re
ss
iv
e
in
teg
ra
ted
m
o
v
in
g
a
v
e
ra
g
e
(A
RIM
A
),
lo
n
g
sh
o
rt
-
term
m
e
m
o
ry
(
L
S
T
M
),
a
n
d
RNN
.
T
h
e
e
x
p
e
rim
e
n
tal
re
su
lt
s
sh
o
w
th
a
t
t
h
e
RNN
o
u
t
p
e
rf
o
r
m
s
A
RIM
A
a
n
d
L
S
T
M
,
w
it
h
a
n
R²
v
a
lu
e
o
f
0
.
9
2
,
a
n
RM
S
E
o
f
0
.
1
3
1
0
7
a
n
d
a
n
M
A
E
o
f
0
.
0
1
7
6
.
T
h
e
p
ro
jec
t
im
p
ro
v
e
d
p
o
w
e
r
r
e
so
u
rc
e
p
lan
n
i
n
g
a
n
d
m
a
n
a
g
e
m
e
n
t,
se
lec
ted
a
n
a
c
c
e
p
tab
le
f
o
re
c
a
stin
g
m
o
d
e
l
RNN
a
n
d
c
o
n
tri
b
u
ted
t
o
f
o
re
c
a
stin
g
tec
h
n
o
l
o
g
y
d
e
v
e
lo
p
m
e
n
ts.
T
h
e
stu
d
y
id
e
n
ti
f
i
e
d
li
m
it
s
in
h
isto
rica
l
d
a
ta
a
v
a
il
a
b
il
it
y
a
n
d
q
u
a
li
ty
,
a
s
w
e
ll
a
s
e
x
tern
a
l
in
f
lu
e
n
c
e
s
a
ff
e
c
ti
n
g
th
e
stu
d
ies
.
RNN
m
o
d
e
ls
c
a
n
h
e
lp
o
p
ti
m
ize
re
so
u
rc
e
a
ll
o
c
a
ti
o
n
a
n
d
im
p
ro
v
e
e
n
e
rg
y
p
lan
n
in
g
.
K
ey
w
o
r
d
s
:
Au
to
r
eg
r
es
s
i
v
e
in
te
g
r
ated
m
o
v
i
n
g
av
er
a
g
e
L
o
n
g
s
h
o
r
t
-
ter
m
m
e
m
o
r
y
Me
an
ab
s
o
lu
te
er
r
o
r
Me
an
s
q
u
ar
e
er
r
o
r
R
ec
u
r
r
en
t n
e
u
r
al
n
et
w
o
r
k
R
o
o
t
m
ea
n
s
q
u
ar
e
er
r
o
r
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
A
z
m
a
n
A
b
Ma
lik
Sch
o
o
l o
f
C
o
m
p
u
ter
Scie
n
ce
,
Un
i
v
er
s
iti
Sain
s
Ma
la
y
s
ia
1
1
8
0
0
USM,
P
u
lau
P
in
an
g
,
Ma
la
y
s
ia
E
m
ail: a
z
m
an
.
ab
d
u
l
@
u
s
m
.
m
y
1.
I
NT
RO
D
UCT
I
O
N
Sig
n
i
f
ica
n
t
d
e
m
a
n
d
g
r
o
w
th
,
a
s
tr
o
n
g
r
elia
n
ce
o
n
f
o
s
s
il
f
u
els,
an
d
r
i
s
in
g
ca
r
b
o
n
e
m
i
s
s
i
o
n
s
d
ef
in
e
C
h
i
n
a
's
en
er
g
y
s
y
s
te
m
.
T
h
e
n
atio
n
'
s
d
ep
en
d
en
ce
o
n
o
il
im
p
o
r
ts
ex
ce
ed
s
5
0
%
b
y
th
e
en
d
o
f
2
0
0
9
,
an
d
it
w
a
s
p
r
o
j
ec
ted
to
6
0
%
in
2
0
1
5
an
d
p
r
ed
icted
u
p
to
7
0
%
in
2
0
3
0
[
1
]
.
P
o
w
er
g
r
id
b
u
s
in
e
s
s
e
s
f
ac
e
is
s
u
e
s
in
m
ee
ti
n
g
lo
ad
n
ee
d
s
d
u
e
to
th
e
d
y
n
a
m
ic
en
er
g
y
e
n
v
ir
o
n
m
e
n
t,
w
h
er
e
a
cc
u
r
ate
f
o
r
ec
asti
n
g
o
f
e
lectr
ic
al
lo
ad
is
cr
u
cial
f
o
r
in
f
o
r
m
ed
d
ec
is
io
n
-
m
a
k
i
n
g
.
An
ef
f
ec
ti
v
e
to
o
l
f
o
r
r
eso
lv
in
g
u
n
ce
r
tai
n
t
y
i
s
r
eq
u
ir
ed
f
o
r
b
etter
co
s
t
an
d
en
er
g
y
ef
f
icien
c
y
d
ec
is
io
n
s
s
u
ch
as
g
en
er
atio
n
s
ch
ed
u
li
n
g
,
s
y
s
te
m
r
el
iab
ilit
y
,
p
o
w
er
o
p
ti
m
iza
tio
n
,
an
d
ec
o
n
o
m
ic
o
p
er
atio
n
s
[
2
]
.
E
s
tab
lis
h
in
g
d
atasets
a
n
d
r
ec
o
r
d
s
f
o
r
a
p
r
o
j
e
ct
is
cr
u
cial,
esp
ec
iall
y
i
n
th
e
en
er
g
y
,
w
ater
,
an
d
en
v
ir
o
n
m
e
n
tal
s
ec
to
r
s
.
Fro
m
d
ata
th
er
e
ar
e
m
a
n
y
i
m
p
o
r
tan
t
asp
ec
t
s
th
at
ca
n
b
e
v
ie
w
ed
f
r
o
m
th
e
d
ata
an
al
y
tics
p
er
s
p
ec
ti
v
e.
Nu
m
er
o
u
s
tec
h
n
iq
u
es
h
a
v
e
b
ee
n
e
m
p
l
o
y
ed
f
o
r
d
ata
ac
q
u
is
itio
n
,
s
u
c
h
as
t
h
e
in
ter
n
et
o
f
th
i
n
g
s
a
n
d
th
e
Scad
a
s
y
s
te
m
.
T
h
ese
t
w
o
co
n
ce
p
ts
ar
e
s
i
m
i
lar
,
s
er
v
i
n
g
a
s
d
ata
s
o
u
r
ce
s
f
o
r
th
e
p
u
r
p
o
s
es
o
f
m
o
n
ito
r
i
n
g
an
d
co
n
tr
o
l.
T
h
e
b
asic
id
ea
i
s
s
i
m
p
le,
w
h
ic
h
i
s
d
er
iv
ed
f
r
o
m
t
h
e
d
ev
elo
p
m
en
t
o
f
g
r
id
co
n
s
tr
u
ctio
n
w
it
h
t
h
e
s
en
s
o
r
co
n
n
ec
tio
n
s
t
h
at
ar
e
p
lace
d
at
im
p
o
r
tan
t
n
o
d
e,
m
icr
o
co
n
tr
o
ller
,
an
d
co
m
p
u
ter
s
y
s
te
m
.
Fig
u
r
e
1
s
h
o
w
s
a
b
asic
b
lo
ck
d
esig
n
o
f
an
elec
tr
ical
g
r
id
w
ith
an
i
n
ter
n
et
o
f
th
i
n
g
s
s
y
s
te
m
.
I
n
th
is
g
r
id
,
th
e
s
en
s
o
r
is
co
n
n
ec
ted
to
th
e
co
n
tr
o
ller
an
d
th
en
to
th
e
co
m
p
u
ter
s
y
s
te
m
o
r
eith
er
to
g
ate
w
a
y
o
r
r
u
n
i
n
t
h
e
d
o
ck
er
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
9
-
4864
I
n
t J
R
ec
o
n
f
i
g
u
r
ab
le
&
E
m
b
ed
d
ed
Sy
s
t
,
Vo
l.
14
,
No
.
2
,
J
u
l
y
20
25
:
497
-
5
0
6
498
Fig
u
r
e
1
.
I
llu
s
tr
atio
n
o
f
p
o
w
er
g
en
er
at
io
n
w
it
h
in
ter
n
et
o
f
t
h
i
n
g
s
s
y
s
t
em
T
h
e
d
ev
elo
p
m
e
n
t o
f
t
h
is
s
y
s
te
m
i
s
n
o
t
li
m
ited
to
d
ata
ac
q
u
i
s
itio
n
,
b
u
t
th
e
r
e
s
u
l
tin
g
d
ata
i
s
also
s
to
r
ed
in
th
e
s
to
r
ag
e
s
y
s
te
m
f
o
r
a
s
p
ec
if
ic
p
u
r
p
o
s
e.
T
h
e
d
ev
elo
p
m
e
n
t
o
f
to
d
a
y
's
tech
n
o
l
o
g
y
w
it
h
ar
tific
ial
in
telli
g
e
n
ce
m
a
k
es
t
h
e
d
ata
f
o
u
n
d
in
a
s
y
s
te
m
d
ev
elo
p
ed
to
an
o
th
er
lev
el.
As
s
h
o
w
n
i
n
Fig
u
r
e
2
,
s
h
o
w
s
a
s
a
m
p
le
o
f
w
o
r
k
s
i
n
p
r
ed
ictio
n
b
ased
o
n
d
ee
p
lear
n
i
n
g
an
a
l
y
s
is
.
T
h
e
w
o
r
k
f
lo
w
b
eg
in
s
w
it
h
d
ataset
ac
q
u
i
s
itio
n
,
f
o
llo
w
ed
b
y
d
ata
an
n
o
tat
io
n
.
T
h
e
in
p
u
t
w
i
ll
th
e
n
b
e
au
g
m
e
n
ted
to
v
ar
io
u
s
s
izes
a
n
d
d
iv
i
d
ed
in
to
tr
ain
in
g
a
n
d
test
s
et
s
b
ased
o
n
a
p
r
ed
eter
m
i
n
ed
r
atio
.
T
h
e
tr
ain
in
g
a
n
d
test
s
et
s
w
il
l
t
h
en
b
e
f
itted
an
d
tr
ain
ed
u
s
i
n
g
a
d
etec
tio
n
alg
o
r
it
h
m
.
Af
ter
t
h
e
tr
ain
i
n
g
i
s
co
m
p
leted
,
t
h
e
b
est
m
o
d
el
w
ill b
e
s
a
v
ed
.
Fin
a
ll
y
,
th
e
b
est
m
o
d
el
w
ill
b
e
u
tili
ze
d
to
e
s
ti
m
ate
t
h
e
test
d
ataset
o
r
n
e
w
d
ata
f
o
r
ev
al
u
atio
n
.
T
h
e
p
r
o
ce
s
s
f
o
r
ass
e
s
s
i
n
g
w
ill
b
e
b
ased
o
n
th
e
ch
o
s
e
n
m
etr
ics,
s
u
c
h
as
m
ea
n
av
er
a
g
e
p
r
ec
is
io
n
(
m
A
P
)
an
d
av
er
ag
e
p
r
ec
is
io
n
(
A
P
)
.
I
f
th
e
m
o
d
el
p
er
f
o
r
m
s
w
ell,
it c
a
n
b
e
ap
p
lied
to
a
r
ea
l
-
w
o
r
ld
p
r
o
b
lem
[
3
]
.
D
a
t
a
s
e
t
A
n
n
o
t
a
t
e
d
d
a
t
a
s
e
t
Te
s
t
s
e
t
T
r
a
i
n
i
n
g
s
e
t
N
e
w
i
m
a
g
e
s
P
r
e
d
i
c
t
i
o
n
R
e
s
u
l
t
o
f
t
h
e
e
v
a
l
u
a
t
i
o
n
M
o
d
e
l
(
1
)
(
2
)
A
n
n
o
t
a
t
i
o
n
(
3
)
D
a
t
a
a
u
g
m
e
n
t
a
t
i
o
n
(
4
)
S
p
l
i
t
(
7
)
P
r
e
d
i
c
t
i
o
n
Fig
u
r
e
2
.
W
o
r
k
f
lo
w
f
o
r
p
r
ed
ic
tio
n
[
3
]
I
n
r
ec
en
t
d
ec
ad
es,
a
s
cie
n
ti
f
ic
m
et
h
o
d
k
n
o
w
n
a
s
p
o
w
er
lo
ad
f
o
r
ec
asti
n
g
h
a
s
b
ee
n
d
e
v
elo
p
ed
[
4
]
-
[
9
]
.
I
n
o
th
er
co
u
n
tr
ie
s
,
f
o
r
ec
asti
n
g
tech
n
o
lo
g
y
h
a
s
b
ee
n
s
t
u
d
ie
d
an
d
is
n
o
w
b
ei
n
g
ap
p
lied
.
L
o
ad
f
o
r
ec
asti
n
g
i
s
cu
r
r
en
tl
y
d
iv
id
ed
in
to
t
w
o
p
h
ase
s
.
Du
r
in
g
t
h
e
f
ir
s
t
p
h
as
e,
w
h
ich
las
ted
f
r
o
m
t
h
e
1
9
6
0
s
to
th
e
1
9
8
0
s
,
co
n
v
e
n
tio
n
al
m
et
h
o
d
s
w
er
e
u
s
ed
.
R
eg
r
es
s
io
n
a
n
al
y
s
i
s
an
d
t
i
m
e
s
er
ie
s
w
er
e
t
w
o
o
f
t
h
e
ec
o
n
o
m
ic
f
o
r
ec
ast
i
n
g
tech
n
iq
u
es
u
s
ed
i
n
th
i
s
s
ta
g
e
[
1
0
]
.
I
n
th
e
s
ec
o
n
d
p
h
ase,
w
h
ic
h
s
p
an
s
th
e
1
9
9
0
s
to
th
e
p
r
esen
t,
lo
ad
f
o
r
ec
asti
n
g
d
ev
elo
p
ed
to
in
clu
d
e
s
o
p
h
is
ticated
alg
o
r
ith
m
s
.
E
x
p
er
t
s
y
s
te
m
s
,
ar
ti
f
icial
n
e
u
r
al
n
et
w
o
r
k
s
,
an
d
f
u
zz
y
lo
g
ic
s
y
s
te
m
s
ar
e
th
e
t
h
r
ee
m
ai
n
ca
teg
o
r
ies
i
n
to
w
h
ic
h
m
o
d
er
n
ar
tif
icia
l
in
tel
lig
e
n
ce
ap
p
r
o
ac
h
es
ca
n
b
e
d
iv
id
ed
[
1
1
]
.
L
o
ad
f
o
r
ec
asti
n
g
w
as
th
e
e
v
e
n
t
u
al
ap
p
licatio
n
o
f
t
h
e
s
e
co
n
ce
p
ts
.
I
n
telli
g
e
n
t
lo
ad
f
o
r
ec
asti
n
g
s
y
s
te
m
s
h
av
e
r
ep
lace
d
co
n
v
e
n
tio
n
al
ec
o
n
o
m
ic
f
o
r
ec
asti
n
g
te
ch
n
iq
u
es
in
th
e
f
ield
o
v
er
ti
m
e.
A
r
ti
f
icial
n
e
u
r
al
n
et
w
o
r
k
s
an
d
ex
p
er
t
s
y
s
te
m
s
ar
e
t
w
o
i
n
s
ta
n
ce
s
o
f
ar
tif
ic
ial
in
telli
g
e
n
ce
-
p
o
w
er
ed
lo
ad
f
o
r
ec
asti
n
g
m
eth
o
d
s
.
T
h
e
n
ec
ess
i
t
y
to
ad
d
r
ess
t
h
e
p
o
w
er
g
r
id
'
s
s
h
o
r
t
-
ter
m
lo
ad
ca
p
ac
it
y
h
a
s
g
r
o
w
n
m
o
r
e
cr
itical
as
t
h
e
p
o
w
e
r
m
ar
k
et
co
n
ti
n
u
es
to
ch
an
g
e.
I
n
th
e
u
p
co
m
i
n
g
y
ea
r
s
,
lo
n
g
-
te
r
m
f
o
r
ec
asti
n
g
w
ill
as
s
is
t
p
lan
s
f
o
r
p
o
w
er
s
y
s
te
m
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
R
ec
o
n
f
i
g
u
r
ab
le
&
E
m
b
ed
d
ed
Sy
s
t
I
SS
N:
2089
-
4864
I
n
ve
s
tig
a
tin
g
th
e
p
erfo
r
ma
n
ce
o
f R
N
N
mo
d
el
to
fo
r
ec
a
s
t th
e
elec
tr
icity
p
o
w
er
…
(
Ha
n
Min
g
yin
g
)
499
ex
p
an
s
io
n
s
a
n
d
en
h
a
n
ce
m
en
t
s
,
w
h
ic
h
w
ill
u
lti
m
atel
y
in
cr
ea
s
e
th
e
p
o
w
er
s
y
s
te
m
's
b
en
e
f
it
s
to
s
o
ciet
y
an
d
th
e
ec
o
n
o
m
y
[
1
1
]
.
A
s
a
r
es
u
lt,
it
is
clea
r
t
h
at
lo
ad
f
o
r
ec
asti
n
g
f
o
r
p
o
w
er
s
y
s
te
m
s
u
s
in
g
d
ata
m
i
n
i
n
g
an
d
o
t
h
er
s
tech
n
iq
u
es
h
as to
b
e
r
esear
ch
e
d
im
m
ed
iatel
y
[
1
2
]
,
[
1
3
]
.
R
eg
r
es
s
io
n
an
al
y
s
is
is
a
s
o
lid
m
et
h
o
d
f
o
r
f
o
r
ec
asti
n
g
lo
ad
u
s
in
g
h
i
s
to
r
ical
d
ata
b
ec
au
s
e
o
f
its
m
at
u
r
e
ass
u
m
p
tio
n
s
,
s
i
m
p
le
co
m
p
u
ta
tio
n
s
,
an
d
s
p
ee
d
y
p
r
o
ce
s
s
in
g
.
Ho
w
e
v
er
,
its
li
m
itatio
n
s
b
ec
o
m
e
ap
p
ar
en
t
i
n
r
ea
l
-
ti
m
e
ap
p
licatio
n
s
a
n
d
n
o
n
li
n
ea
r
ef
f
ec
ts
,
w
h
er
e
it
m
a
y
s
tr
u
g
g
le
to
r
ep
r
esen
t
d
y
n
a
m
i
c
in
ter
ac
tio
n
s
[
1
4
]
.
T
h
e
ti
m
e
s
er
ies
a
n
al
y
s
i
s
m
et
h
o
d
o
r
g
an
ize
s
h
is
to
r
ical
lo
ad
ch
an
g
es
b
y
ti
m
e,
in
d
icat
i
n
g
v
ar
iatio
n
s
o
v
er
ti
m
e
an
d
th
e
e
v
o
l
u
tio
n
o
f
t
h
e
r
u
le
.
T
h
is
ap
p
r
o
ac
h
ca
n
esti
m
ate
f
u
tu
r
e
lo
ad
f
lu
c
tu
at
io
n
s
o
v
e
r
ti
m
e
a
n
d
is
al
s
o
e
m
p
lo
y
ed
i
n
r
o
u
ti
n
e
o
p
er
ati
o
n
s
.
I
n
a
t
y
p
ical
p
o
w
er
g
r
id
o
p
er
atio
n
,
th
e
t
i
m
e
s
er
ies
m
et
h
o
d
'
s
p
r
ed
ictio
n
ac
cu
r
ac
y
is
g
o
o
d
,
b
u
t
it
s
s
m
o
o
th
n
es
s
r
eq
u
ir
e
m
e
n
ts
ar
e
to
o
h
ig
h
.
T
h
e
tech
n
iq
u
e
m
a
y
n
o
lo
n
g
er
h
a
v
e
th
e
d
esire
d
1
im
p
ac
t
d
u
e
to
u
n
u
s
u
al
o
cc
u
r
r
en
ce
s
[
1
5
]
.
A
n
ex
p
er
t
s
y
s
te
m
i
s
a
co
m
p
u
ter
p
r
o
g
r
a
m
m
i
n
g
s
y
s
te
m
d
esig
n
ed
to
m
i
m
ic
h
u
m
a
n
lo
ad
f
o
r
ec
asti
n
g
co
m
p
eten
ce
.
I
t
p
r
o
ce
s
s
es
lo
ad
d
ata
an
d
m
a
k
es
ap
p
r
o
p
r
iate
f
o
r
ec
asti
n
g
p
r
ed
ictio
n
s
b
y
u
ti
lizin
g
ar
tif
ic
ial
in
tel
lig
e
n
ce
a
n
d
a
d
atab
ase
o
f
p
ast
lo
a
d
c
h
an
g
es.
T
o
p
r
ed
ict
s
h
o
r
t
-
ter
m
lo
ad
in
t
h
e
Mu
m
b
ai
ar
ea
,
R
E
L
u
s
ed
an
ex
p
er
t s
y
s
t
e
m
tech
n
iq
u
e
[
1
6
]
.
Po
s
it
iv
e
o
u
tc
o
m
es
h
av
e
b
ee
n
o
b
tain
ed
w
h
en
th
e
im
p
a
ct
o
f
a
lo
a
d
o
n
h
o
li
d
ay
s
an
d
o
th
e
r
u
n
ce
r
tain
ty
is
ass
ess
e
d
u
s
in
g
h
u
m
an
ex
p
e
r
i
en
ce
.
N
o
n
eth
e
less
,
th
e
p
o
w
er
en
v
ir
o
n
m
en
t
v
ar
ies
b
y
r
eg
i
o
n
,
w
h
ich
l
ea
d
s
t
o
a
co
m
p
lic
at
ed
c
o
m
p
u
ter
p
r
o
g
r
a
m
an
d
a
lo
t
o
f
d
at
a
ar
e
r
e
q
u
i
r
e
d
.
A
n
in
tell
ig
en
t
in
f
o
r
m
ati
o
n
p
r
o
ce
s
s
in
g
te
ch
n
iq
u
e
th
at
im
itat
es
th
e
w
o
r
k
in
g
s
o
f
th
e
h
u
m
an
b
r
ain
is
th
e
a
r
tif
i
cial
n
eu
r
al
n
etw
o
r
k
.
I
t
is
p
r
o
f
icien
t
at
h
an
d
l
in
g
co
m
p
lic
at
ed
n
o
n
-
lin
ea
r
in
te
r
a
c
tio
n
s
b
etw
ee
n
in
p
u
t
v
a
r
i
ab
les
a
n
d
p
r
e
d
ic
te
d
o
u
t
p
u
t
,
le
ar
n
in
g
t
h
e
b
est
p
a
r
am
ete
r
s
,
an
d
ass
ess
in
g
an
d
r
es
o
lv
in
g
s
to
ch
asti
c
u
n
c
er
t
ain
ty
an
d
co
m
p
lex
n
o
n
-
lin
e
a
r
r
e
lati
o
n
s
h
i
p
p
r
o
b
l
em
s
[
1
7
]
,
[
18
]
.
T
h
e
ap
p
r
o
a
ch
is
lim
ite
d
t
o
s
m
all
s
am
p
le
le
ar
n
in
g
an
d
is
b
as
e
d
o
n
em
p
ir
i
ca
l
r
is
k
m
in
i
m
izati
o
n
.
T
h
e
s
tu
d
y
aim
s
to
an
a
ly
ze
th
e
ef
f
ic
ien
cy
o
f
ti
m
e
s
er
ies
m
o
d
els,
th
at
a
r
e
au
t
o
r
eg
r
es
s
iv
e
in
teg
r
a
te
d
m
o
v
in
g
av
e
r
ag
e
(
A
R
I
MA
)
,
lo
n
g
s
h
o
r
t
-
te
r
m
m
e
m
o
r
y
(
L
S
T
M
)
,
an
d
r
ec
u
r
r
en
t
n
eu
r
al
n
etw
o
r
k
(
R
NN
)
m
o
d
e
ls
in
p
r
ed
ict
in
g
p
o
w
er
co
n
s
u
m
p
tio
n
b
y
g
ath
e
r
in
g
el
ec
t
r
ic
ity
lo
ad
d
at
a
an
d
a
p
p
ly
in
g
th
em
.
Me
t
r
i
cs
in
clu
d
in
g
m
ea
n
s
q
u
ar
e
er
r
o
r
(
MS
E
)
,
m
ea
n
a
b
s
o
lu
te
p
r
ec
is
i
o
n
(
MA
P
)
,
an
d
r
o
o
t
m
ea
n
s
q
u
ar
e
er
r
o
r
(
R
MS
E
)
a
r
e
u
s
e
d
t
o
ass
ess
th
e
m
o
d
els'
p
e
r
f
o
r
m
an
ce
.
T
h
e
m
ain
o
b
jecti
v
e
is
t
o
d
et
er
m
in
e
w
h
ich
m
o
d
e
l
is
m
o
s
t
a
p
p
r
o
p
r
iat
e
f
o
r
th
is
i
n
v
esti
g
ati
o
n
.
I
n
th
e
m
ea
n
w
h
ile,
th
e
is
s
u
e
o
f
th
e
ill
o
g
ic
al
d
is
tr
ib
u
t
io
n
o
f
e
lec
tr
ici
t
y
d
em
an
d
c
an
b
e
r
es
o
lv
e
d
an
d
en
e
r
g
y
w
aste
c
an
b
e
p
r
ev
en
t
e
d
b
y
in
teg
r
a
tin
g
s
h
o
r
t
-
t
er
m
lo
ad
f
o
r
e
ca
s
t
in
g
t
ec
h
n
iq
u
es
w
ith
d
em
an
d
r
esp
o
n
s
e
o
f
e
lec
tr
ici
ty
co
n
s
u
m
p
tio
n
.
T
h
e
p
o
w
er
g
r
i
d
b
u
s
in
ess
ca
n
s
el
ec
t
th
e
m
o
s
t
ap
p
r
o
p
r
ia
te
m
o
d
e
l
b
as
e
d
o
n
t
h
e
s
tu
d
y
'
s
f
in
d
in
g
s
.
A
d
d
it
io
n
a
lly
,
th
er
e
is
a
l
o
t
o
f
r
o
o
m
f
o
r
im
p
r
o
v
em
en
t
in
th
e
p
o
w
er
g
r
i
d
'
s
ef
f
ici
en
cy
an
d
d
e
p
en
d
a
b
il
ity
th
r
o
u
g
h
th
e
in
teg
r
a
ti
o
n
o
f
s
h
o
r
t
-
te
r
m
lo
a
d
p
r
e
d
i
cti
o
n
an
d
d
em
an
d
r
e
s
p
o
n
s
e
t
ec
h
n
o
lo
g
i
es.
W
ith
th
i
s
s
tr
ateg
y
,
el
ec
tr
i
ca
l
r
es
o
u
r
ce
s
ca
n
b
e
u
s
ed
m
o
r
e
ef
f
ec
tiv
ely
,
an
d
th
e
s
y
s
tem
ca
n
r
ea
c
t
q
u
i
ck
ly
to
v
a
r
i
ati
o
n
s
in
d
e
m
an
d
.
Mo
r
e
o
v
e
r
,
it
g
iv
es
c
o
n
s
u
m
er
s
th
e
a
b
ili
ty
to
tak
e
an
ac
tiv
e
r
o
le
in
c
o
n
t
r
o
lli
n
g
th
ei
r
p
o
w
er
u
s
ag
e
,
em
p
o
w
er
in
g
th
em
to
m
ak
e
k
n
o
w
led
g
e
ab
le
d
e
cisi
o
n
s
an
d
h
elp
c
r
ea
te
a
m
o
r
e
s
u
s
ta
in
a
b
le
en
e
r
g
y
f
u
tu
r
e
[
1
7
]
,
[
18
]
.
O
r
g
an
iza
ti
o
n
s
ca
n
h
el
p
p
r
o
m
o
te
s
u
s
ta
in
ab
le
d
ev
el
o
p
m
en
t
in
Gu
an
g
zh
o
u
C
ity
an
d
o
f
f
er
u
s
ef
u
l
in
f
o
r
m
ati
o
n
f
o
r
en
e
r
g
y
m
an
ag
e
m
en
t
b
y
d
ev
e
lo
p
in
g
a
s
im
p
lif
ie
d
an
d
a
c
cu
r
a
te
p
o
w
er
d
em
an
d
f
o
r
ec
asti
n
g
m
o
d
el.
A
f
e
w
elec
tr
ical
co
m
p
a
n
ies
h
a
v
e
s
u
cc
ess
f
u
ll
y
u
s
ed
ar
tif
icial
n
eu
r
al
n
et
w
o
r
k
to
m
o
d
i
f
y
i
n
te
r
n
et
lo
ad
.
I
n
co
m
p
ar
is
o
n
to
th
e
s
tan
d
ar
d
p
r
e
d
icto
r
,
th
e
ex
p
er
i
m
en
ta
l
d
ata
d
em
o
n
s
tr
ate
th
at
th
e
tech
n
iq
u
e
r
ed
u
ce
s
er
r
o
r
b
y
4
1
%
an
d
tr
ai
n
in
g
ti
m
e
b
y
6
6
%
[
1
9
]
.
Use
th
e
g
en
et
ic
alg
o
r
ith
m
(
G
A
)
to
f
i
n
d
th
e
o
p
ti
m
al
ti
m
e
la
g
an
d
n
u
m
b
er
o
f
la
y
er
s
to
m
a
x
i
m
ize
th
e
p
er
f
o
r
m
an
ce
o
f
L
ST
M
m
o
d
els.
Fin
d
in
g
s
:
w
i
th
a
C
V
(
R
MSE
)
o
f
0
.
5
6
%
o
n
av
er
ag
e
a
n
d
0
.
6
1
%
o
v
er
th
e
s
h
o
r
t
ter
m
,
L
ST
M
-
R
NN
s
h
o
w
s
r
ed
u
ce
d
f
o
r
ec
ast
er
r
o
r
s
.
Hig
h
er
p
r
ed
ictio
n
ac
cu
r
ac
y
ca
n
b
e
ac
h
iev
ed
b
y
o
p
tim
izin
g
f
ea
t
u
r
es,
l
a
g
s
,
la
y
e
r
s
,
an
d
L
ST
M
co
n
f
i
g
u
r
atio
n
s
.
T
h
is
ap
p
r
o
ac
h
n
o
t
o
n
l
y
allo
w
s
f
o
r
b
etter
u
tili
z
atio
n
o
f
p
o
w
er
r
eso
u
r
ce
s
b
u
t
also
en
ab
les
t
h
e
g
r
id
to
r
esp
o
n
d
p
r
o
m
p
tl
y
to
f
l
u
ctu
a
tio
n
s
i
n
d
e
m
a
n
d
[
20
]
.
T
h
e
s
t
u
d
y
f
in
d
s
th
a
t
t
h
e
m
ea
n
a
b
s
o
lu
te
er
r
o
r
(
MA
E
)
a
n
d
R
M
SE
o
f
m
ed
iu
m
-
a
n
d
lo
n
g
-
d
is
ta
n
ce
f
o
r
ec
asts
w
er
e
r
ed
u
ce
d
[
2
1
]
.
T
h
e
m
ea
n
ab
s
o
lu
te
p
er
ce
n
tag
e
er
r
o
r
(
MA
P
E
)
m
ea
s
u
r
e
is
u
s
ed
to
ass
es
s
m
o
d
els.
Fo
r
au
to
r
eg
r
es
s
iv
e
m
o
v
i
n
g
av
er
ag
e
(
A
R
M
A)
,
A
R
I
M
A
,
an
d
au
to
r
eg
r
e
s
s
i
v
e
in
teg
r
ated
m
o
v
i
n
g
av
er
ag
e
w
it
h
ex
p
la
n
ato
r
y
v
ar
iab
le
(
A
R
I
M
A
X
)
,
th
e
f
o
r
ec
ast
er
r
o
r
lev
els
ar
e
1
7
.
7
%,
4
%,
an
d
3
.
6
%,
co
r
r
esp
o
n
d
in
g
l
y
.
I
n
ter
m
s
o
f
f
o
r
ec
ast
ac
cu
r
ac
y
,
A
R
M
A
p
er
f
o
r
m
s
w
o
r
s
e
th
a
n
AR
I
M
A
an
d
A
R
I
M
A
X
m
o
d
els.
R
esear
ch
s
u
g
g
e
s
ts
th
at
A
R
I
MA
X
m
o
d
els
o
u
tp
er
f
o
r
m
AR
I
MA
m
o
d
els
b
y
a
l
ittl
e
m
ar
g
in
[
2
2
]
.
Un
d
er
id
ea
l
w
ea
t
h
er
c
o
n
d
itio
n
s
,
t
h
e
R
MS
E
ac
cu
r
ac
y
ca
n
ap
p
r
o
ac
h
4
.
6
2
%
an
d
th
e
L
ST
M
m
o
d
el
ac
cu
r
ac
y
ca
n
r
ea
ch
4
.
6
2
%.
T
h
e
r
ec
o
m
m
e
n
d
ed
m
eth
o
d
ac
h
ie
v
es
a
h
i
g
h
d
eg
r
ee
o
f
f
o
r
ec
ast
ac
cu
r
ac
y
an
d
e
f
f
e
ctiv
el
y
ca
p
tu
r
e
s
t
h
e
d
y
n
a
m
ic
ch
ar
ac
ter
i
s
tics
o
f
les
s
-
t
h
an
-
id
ea
l
w
ea
t
h
er
co
n
d
itio
n
s
[
2
3
].
Utilizi
n
g
a
d
ee
p
n
eu
r
al
n
et
w
o
r
k
,
q
u
an
t
ile
r
eg
r
es
s
io
n
is
u
tili
ze
d
to
p
r
ed
ict
p
o
w
er
c
o
n
s
u
m
p
tio
n
ac
co
r
d
in
g
to
p
r
o
b
ab
ilit
y
d
en
s
it
y
.
T
h
e
er
r
o
r
v
alu
e
is
a
t
its
l
o
w
est
w
h
e
n
d
ee
p
lear
n
i
n
g
i
s
u
s
ed
.
T
h
r
ee
v
alu
e
s
h
av
e
b
ee
n
id
en
t
if
ied
[
2
4
]
:
3
%
f
o
r
M
A
P
E
,
6
%
f
o
r
m
ea
n
r
elat
iv
e
p
er
ce
n
ta
g
e
er
r
o
r
(
MRP
E
)
,
an
d
5
9
4
f
o
r
MA
E
.
T
h
e
ex
p
er
i
m
en
tal
r
es
u
lts
s
h
o
w
t
h
at
th
e
d
ee
p
lear
n
in
g
s
tr
at
eg
y
p
er
f
o
r
m
s
b
etter
th
a
n
t
h
e
r
an
d
o
m
f
o
r
est
an
d
g
r
ad
ien
t
b
o
o
s
tin
g
m
ac
h
in
e
m
eth
o
d
s
in
ter
m
s
o
f
p
r
ed
ictio
n
er
r
o
r
.
T
h
e
d
ee
p
lea
r
n
in
g
m
o
d
el
s
u
g
g
est
s
th
a
t
th
e
m
o
s
t
i
m
p
o
r
tan
t
v
ar
iab
les
f
o
r
th
e
f
ea
t
u
r
e
s
elec
tio
n
p
r
o
b
lem
ar
e
t
h
o
s
e
li
n
k
ed
to
te
m
p
e
r
atu
r
e,
w
ee
k
l
y
,
a
n
d
m
o
n
t
h
l
y
c
y
cles.
co
n
s
id
er
in
g
co
n
s
u
m
p
tio
n
is
m
o
s
t
af
f
ec
ted
b
y
s
u
m
m
er
h
i
g
h
s
.
s
u
b
s
ta
n
tia
l
i
m
p
ac
t
o
n
p
o
w
er
co
n
s
u
m
p
tio
n
[
2
5
]
.
T
h
e
p
ap
er
s
u
g
g
e
s
ts
u
s
i
n
g
L
ST
M,
ch
ao
ti
c
ti
m
e
s
er
ies,
in
te
lli
g
en
t
o
p
tim
izatio
n
al
g
o
r
ith
m
s
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
9
-
4864
I
n
t J
R
ec
o
n
f
i
g
u
r
ab
le
&
E
m
b
ed
d
ed
Sy
s
t
,
Vo
l.
14
,
No
.
2
,
J
u
l
y
20
25
:
497
-
5
0
6
500
m
ap
p
in
g
,
an
d
s
h
o
r
t
-
ter
m
p
o
w
er
lo
ad
f
o
r
ec
asti
n
g
to
r
ed
u
ce
m
an
u
al
d
eb
u
g
g
in
g
,
i
m
p
r
o
v
e
p
r
ed
ictio
n
ac
cu
r
ac
y
,
an
d
ex
te
n
d
lo
ad
f
o
r
ec
ast
d
u
r
atio
n
.
W
h
en
co
m
p
ar
ed
to
L
ST
M
p
r
e
d
ictio
n
,
th
e
m
et
h
o
d
u
s
ed
i
n
t
h
is
s
tu
d
y
in
cr
ea
s
es
p
r
ed
ictio
n
ac
c
u
r
ac
y
b
y
6
1
.
8
7
%
in
ter
m
s
o
f
R
M
SE.
T
h
er
e
ar
e
tim
e
s
w
h
e
n
t
h
e
f
o
r
ec
ast
er
r
o
r
is
r
ed
u
ce
d
b
y
5
0
%
w
ith
in
t
h
e
4
0
-
ti
m
e
p
r
ed
ictio
n
w
i
n
d
o
w
[2
6
]
.
R
esid
en
tial
lo
ad
s
in
u
r
b
an
ar
ea
s
,
co
m
m
er
cial
lo
ad
s
,
r
u
r
al
lo
ad
s
,
i
n
d
u
s
tr
ia
l
l
o
ad
s
,
an
d
o
th
er
s
o
r
t
s
o
f
lo
ad
s
ar
e
a
m
o
n
g
t
h
e
s
e
v
er
al
k
i
n
d
s
o
f
p
o
w
er
s
y
s
te
m
lo
ad
s
.
Dif
f
er
e
n
t lo
ad
s
h
a
v
e
d
if
f
er
en
t c
h
ar
ac
ter
is
tic
s
an
d
r
u
le
s
[
2
7
]
-
[
2
9
].
2.
M
E
T
H
O
D
T
h
is
p
ap
er
'
s
ap
p
r
o
ac
h
in
clu
d
es
co
llectio
n
o
f
d
atasets
,
p
r
ep
r
o
ce
s
s
in
g
o
f
t
h
o
s
e
d
atase
ts
,
m
o
d
el
s
elec
tio
n
,
a
n
d
p
er
f
o
r
m
an
ce
te
s
tin
g
u
s
i
n
g
R
M
SE,
M
A
E
,
an
d
MSE
to
co
m
p
ar
e
an
d
co
n
t
r
ast
th
r
ee
m
o
d
els
:
AR
I
M
A
,
L
ST
M,
an
d
R
NN.
Fi
g
u
r
e
3
s
h
o
w
s
th
e
f
lo
w
o
f
r
esea
r
ch
m
et
h
o
d
o
lo
g
y
.
Fig
u
r
e
3
.
R
esear
ch
m
et
h
o
d
o
lo
g
y
2
.
1
.
Da
t
a
s
et
T
h
e
s
tu
d
y
co
llected
t
h
r
ee
d
atasets
,
t
h
e
f
ir
s
t
d
ataset
i
s
a
r
eg
io
n
al
elec
tr
ical
lo
ad
d
ataset
r
ec
o
r
d
ed
at
15
-
m
i
n
u
te
in
ter
v
als
as
s
h
o
w
n
o
n
T
ab
le
1
.
T
h
e
s
ec
o
n
d
d
ata
s
et
is
an
av
er
a
g
e
elec
tr
icit
y
c
o
n
s
u
m
p
tio
n
d
ataset
f
o
r
d
if
f
er
en
t
i
n
d
u
s
tr
ie
s
a
s
s
h
o
w
n
i
n
T
ab
le
2
.
T
h
e
th
ir
d
d
ataset
(
as
s
h
o
w
n
i
n
T
ab
le
3
)
is
a
d
ataset
o
n
m
eteo
r
o
lo
g
y
,
w
h
ich
r
ec
o
r
d
s
attr
ib
u
tes
s
u
ch
as
te
m
p
er
atu
r
e
an
d
w
i
n
d
s
p
ee
d
.
T
h
e
f
ir
s
t
d
atas
et
is
r
ec
o
r
d
e
d
f
r
o
m
J
an
u
ar
y
2
0
1
8
to
A
u
g
u
s
t
2
0
2
1
,
it
h
as
t
w
o
attr
ib
u
te
s
.
A
n
d
t
h
e
s
ec
o
n
d
d
ataset
is
r
ec
o
r
d
ed
f
r
o
m
y
ea
r
2
0
1
9
t
o
2
0
2
1
,
it h
as f
o
u
r
attr
ib
u
tes.
T
ab
le
1
.
A
1
5
-
m
i
n
u
te
i
n
ter
v
al
s
r
eg
io
n
al
p
o
w
er
lo
ad
d
ataset
(
d
ataset
)
A
t
t
r
i
b
u
t
e
n
a
me
A
t
t
r
i
b
u
t
e
t
y
p
e
D
a
t
a
t
i
me
D
a
t
e
T
o
t
a
l
p
o
w
e
r
u
sag
e
(
k
w
)
N
u
me
r
i
c
T
ab
le
2
.
A
v
er
ag
e
p
o
w
er
lo
ad
d
ataset
f
o
r
d
if
f
er
en
t i
n
d
u
s
tr
ies
(
d
ataset
)
A
t
t
r
i
b
u
t
e
n
a
me
A
t
t
r
i
b
u
t
e
t
y
p
e
S
e
c
t
o
r
t
y
p
e
C
a
t
e
g
o
r
i
c
a
l
D
a
t
a
t
i
me
D
a
t
e
A
v
e
r
a
g
e
p
o
w
e
r
max
(
k
w
)
N
u
me
r
i
c
A
v
e
r
a
g
e
p
o
w
e
r
mi
n
(
k
w
)
N
u
me
r
i
c
T
ab
le
3
.
C
li
m
ate
d
ataset
(
d
ataset
)
A
t
t
r
i
b
u
t
e
n
a
me
A
t
t
r
i
b
u
t
e
t
y
p
e
D
a
t
e
D
a
t
e
W
e
a
t
h
e
r
C
a
t
e
g
o
r
i
c
a
l
M
a
x
t
e
mp
e
r
a
t
u
r
e
N
u
me
r
i
c
M
i
n
t
e
mp
e
r
a
t
u
r
e
N
u
me
r
i
c
D
a
y
t
i
me
w
i
n
d
C
a
t
e
g
o
r
i
c
a
l
N
i
g
h
t
w
i
n
d
C
a
t
e
g
o
r
i
c
a
l
2.
2
.
P
re
pro
ce
s
s
ing
T
o
p
r
ed
ict
th
e
f
u
t
u
r
e
lo
ad
w
i
th
h
is
to
r
ical
lo
ad
d
ata,
ac
cu
r
a
c
y
a
n
d
in
teg
r
it
y
o
f
t
h
e
d
ata
i
s
t
h
e
f
ir
s
t
co
n
d
itio
n
.
D
u
e
to
th
e
ex
ter
n
al
o
r
in
ter
n
al
r
a
n
d
o
m
f
a
u
lt,
co
m
m
u
n
icatio
n
s
i
g
n
a
l
i
n
ter
f
e
r
en
ce
an
d
ar
ti
f
icial
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
R
ec
o
n
f
i
g
u
r
ab
le
&
E
m
b
ed
d
ed
Sy
s
t
I
SS
N:
2089
-
4864
I
n
ve
s
tig
a
tin
g
th
e
p
erfo
r
ma
n
ce
o
f R
N
N
mo
d
el
to
fo
r
ec
a
s
t th
e
elec
tr
icity
p
o
w
er
…
(
Ha
n
Min
g
yin
g
)
501
r
ec
o
r
d
in
g
,
th
er
e
is
p
ar
t
o
f
t
h
e
ti
m
e
n
o
d
e
d
ata
m
is
s
in
g
o
r
ab
n
o
r
m
al.
So
th
at
it
is
n
ec
es
s
ar
y
to
an
al
y
ze
an
d
co
r
r
ec
tio
n
o
f
h
is
to
r
ical
d
ata
was n
ee
d
ed
b
ef
o
r
e
estab
lis
h
in
g
t
h
e
p
r
ed
ictio
n
m
o
d
el.
2
.
3
.
M
o
del
s
elec
t
io
n
T
h
e
A
R
I
M
A
m
o
d
el
is
a
ti
m
e
s
er
ies
an
al
y
s
is
m
eth
o
d
u
s
ed
t
o
m
o
d
el
an
d
p
r
ed
ict
ti
m
e
s
er
i
es
d
ata.
I
t
co
n
s
is
ts
o
f
t
w
o
p
ar
ts
:
au
to
r
eg
r
ess
i
v
e
an
d
m
o
v
i
n
g
a
v
er
ag
e
.
T
h
e
m
o
d
el
d
ec
o
m
p
o
s
es
ti
m
e
-
s
er
ies
d
ata
in
t
o
au
to
r
eg
r
es
s
iv
e
co
m
p
o
n
e
n
t
s
,
m
o
v
i
n
g
m
ea
n
co
m
p
o
n
en
t
s
,
an
d
r
an
d
o
m
er
r
o
r
ter
m
s
.
T
h
e
au
to
r
eg
r
es
s
iv
e
co
m
p
o
n
e
n
t
r
ep
r
esen
t
s
th
e
co
r
r
elatio
n
b
et
w
ee
n
cu
r
r
en
t
an
d
p
ast
o
b
s
er
v
atio
n
s
,
t
h
e
m
o
v
in
g
av
er
ag
e
co
m
p
o
n
e
n
t
r
ep
r
e
s
en
ts
th
e
co
r
r
elatio
n
b
etw
ee
n
cu
r
r
en
t
an
d
p
ast
er
r
o
r
s
,
an
d
th
e
r
an
d
o
m
er
r
o
r
ter
m
r
ep
r
esen
ts
f
l
u
ct
u
atio
n
s
th
at
ca
n
n
o
t b
e
ex
p
lai
n
ed
b
y
th
ese
co
m
p
o
n
e
n
ts
.
L
ST
M
is
a
v
ar
ian
t o
f
tr
ad
itio
n
al
R
N
N
t
h
at
ef
f
ec
tiv
e
l
y
ca
p
tu
r
e
s
s
e
m
a
n
tic
a
s
s
o
ciatio
n
s
b
et
w
ee
n
lo
n
g
s
eq
u
en
c
e
s
an
d
r
ed
u
ce
s
th
e
p
h
en
o
m
en
o
n
o
f
g
r
ad
ien
t
d
is
ap
p
ea
r
an
ce
o
r
ex
p
lo
s
io
n
.
I
ts
m
ai
n
f
ea
t
u
r
e
is
th
e
co
n
tr
o
l
o
f
g
ate
s
tr
u
ctu
r
e,
i
n
clu
d
i
n
g
f
o
r
g
etti
n
g
,
in
p
u
t,
ce
l
l
s
tate,
an
d
o
u
tp
u
t
g
ates,
w
h
ic
h
ad
d
s
a
"
p
r
o
ce
s
s
o
r
"
to
j
u
d
g
e
in
f
o
r
m
atio
n
u
t
ili
t
y
,
en
ab
li
n
g
b
etter
ti
m
e
s
er
ies
tas
k
s
a
n
d
s
o
lv
i
n
g
lo
n
g
-
ter
m
d
ep
en
d
en
ce
is
s
u
e
s
ca
u
s
ed
b
y
R
NN
b
ac
k
p
r
o
p
ag
atio
n
d
u
r
in
g
tr
ai
n
in
g
.
A
R
NN
is
an
ar
tif
icial
n
eu
r
al
n
et
w
o
r
k
w
it
h
i
n
ter
n
al
r
i
n
g
c
o
n
n
ec
tio
n
s
u
s
ed
f
o
r
p
r
o
ce
s
s
in
g
s
eq
u
e
n
ce
d
ata.
I
ts
k
e
y
f
e
atu
r
e
is
its
lo
o
p
s
,
allo
w
i
n
g
in
f
o
r
m
at
io
n
t
o
cir
cu
l
ate
an
d
f
ac
ilit
a
te
th
e
s
to
r
ag
e
a
n
d
p
r
o
ce
s
s
in
g
o
f
s
eq
u
e
n
ce
i
n
f
o
r
m
at
io
n
.
2.
4
.
E
v
a
lua
t
ing
m
o
del
perf
o
r
m
a
nce
s
T
h
e
b
est
m
o
d
el
f
o
r
p
r
ed
ictin
g
p
o
w
er
co
n
s
u
m
p
tio
n
d
ata
was
s
elec
ted
af
ter
ea
c
h
m
o
d
el
h
ad
b
ee
n
ev
alu
a
ted
u
s
in
g
R
MSE
,
M
A
E
,
an
d
MSE
.
O
n
e
w
a
y
to
m
ea
s
u
r
e
th
e
ac
c
u
r
ac
y
o
f
a
p
r
ed
ictio
n
is
b
y
lo
o
k
i
n
g
at
it
s
MA
E
.
T
h
is
s
ca
le
-
d
ep
en
d
en
t
m
etr
ic
m
i
n
i
m
is
e
s
t
h
e
g
ap
a
m
o
n
g
b
o
th
n
e
g
ati
v
e
a
n
d
p
o
s
itiv
e
er
r
o
r
s
in
o
r
d
er
to
p
r
o
p
er
ly
r
ef
lect
p
r
ed
ictio
n
er
r
o
r
.
In
(
1
)
m
a
y
b
e
u
s
ed
to
d
eter
m
i
n
e
M
A
E
[
2
8
].
=
1
∑
|
−
̂
=
1
|
(
1
)
T
h
e
m
ea
n
s
q
u
ar
ed
er
r
o
r
(
MSE
)
is
a
m
ea
s
u
r
e
o
f
t
h
e
av
er
a
g
e
s
q
u
ar
ed
d
ev
iatio
n
b
et
w
ee
n
th
e
ex
p
ec
ted
an
d
ac
tu
al
v
alu
e
s
[
2
9
]
.
I
t is d
e
ter
m
i
n
ed
b
y
(
2
)
.
=
1
∑
|
−
̂
|
2
=
1
(
2
)
T
h
e
R
MSE
m
ea
s
u
r
es
t
h
ese
p
r
ed
ictio
n
m
is
ta
k
es.
R
MSE
a
s
s
h
o
w
n
i
n
(
3
)
.
T
h
e
r
esid
u
als,
a
m
ea
s
u
r
e
o
f
th
e
d
is
p
er
s
io
n
o
f
th
e
d
ata
p
o
i
n
ts
ar
o
u
n
d
t
h
e
r
eg
r
e
s
s
io
n
li
n
e
,
s
h
o
u
ld
b
e
co
n
s
id
er
ed
f
ir
s
t.
An
i
n
d
icato
r
o
f
t
h
e
d
is
p
er
s
io
n
o
f
th
e
s
e
r
esid
u
al
s
i
s
th
e
R
M
SE.
I
n
o
r
d
er
to
v
alid
ate
th
e
ex
p
er
i
m
e
n
tal
m
o
d
els,
t
h
is
s
tatis
t
ic
is
o
f
te
n
ca
lcu
lated
an
d
u
tili
s
ed
i
n
r
eg
r
e
s
s
io
n
a
n
al
y
s
i
s
,
cli
m
a
to
lo
g
y
,
a
n
d
f
o
r
ec
asti
n
g
[
18
].
=
√
1
∑
|
−
̂
|
2
=
1
(
3
)
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
is
s
ec
tio
n
p
r
o
v
id
es
an
i
n
-
d
ep
th
lo
o
k
at
t
h
e
ev
a
lu
atio
n
an
d
r
esu
lts
o
f
t
h
r
ee
d
if
f
er
e
n
t
m
o
d
el
s
(
AR
I
M
A
,
L
ST
M,
an
d
R
NN)
u
s
ed
to
f
o
r
ec
ast
elec
tr
icit
y
lo
ad
d
ata.
T
h
e
an
aly
s
is
co
v
er
s
r
eg
io
n
al
p
o
w
er
lo
ad
d
atasets
at
1
5
-
m
in
u
te
i
n
ter
v
a
ls
(
Data
s
et
)
an
d
a
co
m
b
i
n
ed
d
ataset
(
Me
r
g
ed
Data
s
et
)
f
o
cu
s
i
n
g
o
n
av
er
a
g
e
ma
x
i
m
u
m
p
o
w
er
lo
ad
s
f
o
r
lar
g
e
in
d
u
s
tr
ial
p
o
w
er
.
Data
s
et
is
a
s
in
g
le
v
ar
iab
le
in
p
u
t
an
d
a
s
in
g
le
v
ar
iab
le
o
u
tp
u
t
f
o
r
r
esear
ch
p
u
r
p
o
s
es.
T
h
e
m
er
g
ed
d
atase
t
i
s
a
r
esear
ch
p
u
r
p
o
s
e
co
n
tai
n
i
n
g
ex
ter
n
a
l
v
ar
iab
le
i
n
p
u
t
a
n
d
s
in
g
le
o
u
tp
u
t.
U
s
i
n
g
,
R
MSE
,
MA
E
,
a
n
d
MSE
a
s
p
er
f
o
r
m
a
n
ce
m
etr
ics,
h
y
p
er
p
ar
a
m
eter
co
n
f
i
g
u
r
atio
n
s
,
a
n
d
m
o
d
el
s
w
er
e
p
lace
d
in
to
g
r
id
s
ea
r
ch
f
o
r
au
to
m
a
ted
s
ea
r
ch
es
f
o
r
s
elec
ted
o
p
ti
m
al
m
o
d
el
h
y
p
er
p
ar
am
eter
co
n
f
i
g
u
r
atio
n
s
w
h
ile
tr
ain
in
g
th
e
m
o
d
els,
f
o
llo
w
ed
b
y
p
r
ed
ictio
n
s
.
E
ac
h
m
o
d
el
'
s
o
p
tim
al
p
ar
a
m
eter
s
an
d
s
u
b
s
eq
u
en
t
p
er
f
o
r
m
an
ce
m
etr
ics
w
er
e
ex
p
lo
r
ed
to
g
ain
a
co
m
p
r
e
h
en
s
iv
e
u
n
d
er
s
tan
d
i
n
g
o
f
th
eir
p
r
ed
ictiv
e
ca
p
ab
ilit
ies.
Ov
er
all
r
es
u
lt
d
at
aset
as s
h
o
w
n
i
n
T
ab
le
4
.
T
ab
le
4
.
T
h
e
r
esu
lts
o
f
u
s
i
n
g
t
h
r
ee
m
o
d
els i
n
th
e
d
atase
t
M
o
d
e
l
R
M
S
E
M
A
E
M
S
E
R²
A
R
I
M
A
9
9
5
0
.
3
5
5
5
1
8
.
9
6
9
9
0
0
9
3
9
7
.
0
3
0
.
4
2
L
S
T
M
0
.
1
2
5
6
3
0
.
0
5
0
9
0
.
0
0
4
7
3
7
0
.
4
8
5
R
N
N
0
.
1
3
1
0
7
0
.
0
1
7
6
0
.
0
0
0
5
1
2
0
.
9
2
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
9
-
4864
I
n
t J
R
ec
o
n
f
i
g
u
r
ab
le
&
E
m
b
ed
d
ed
Sy
s
t
,
Vo
l.
14
,
No
.
2
,
J
u
l
y
20
25
:
497
-
5
0
6
502
Fro
m
Fig
u
r
e
4
,
th
e
R
NN
m
o
d
el
o
u
tp
er
f
o
r
m
s
th
e
L
ST
M
m
o
d
el
in
ter
m
s
o
f
R
²,
in
d
icati
n
g
a
b
etter
f
it.
T
h
e
L
ST
M
m
o
d
el
h
as
a
s
li
g
h
tl
y
lo
w
er
R
MSE
,
s
u
g
g
esti
n
g
s
lig
h
tl
y
b
etter
ac
cu
r
ac
y
i
n
p
r
ed
ictin
g
t
h
e
tar
g
et
v
ar
iab
le.
T
h
e
R
NN
m
o
d
el
s
i
g
n
i
f
ica
n
tl
y
o
u
tp
er
f
o
r
m
s
th
e
L
S
T
M
m
o
d
el
in
ter
m
s
o
f
R
²
,
MA
E
,
an
d
MSE
,
in
d
icati
n
g
b
etter
ac
c
u
r
ac
y
a
n
d
p
r
ed
ictiv
e
p
er
f
o
r
m
an
ce
.
R
NN
s
co
r
e
0
.
9
2
an
d
L
ST
M
s
co
r
e
0
.
4
8
5
.
T
ab
le
5
s
h
o
w
s
a
r
es
u
lt
o
f
u
s
i
n
g
t
h
r
ee
m
o
d
els
i
n
th
e
m
er
g
e
d
ataset
f
o
r
lar
g
e
in
d
u
s
tr
ial
p
o
w
er
u
s
ag
e.
B
ased
o
n
t
h
i
s
tab
le,
th
e
o
u
tp
u
t
ar
e
s
tab
le
a
n
d
th
e
alg
o
r
it
h
m
,
ca
n
b
e
co
n
s
i
d
er
ed
.
Fig
u
r
e
5
,
b
lu
e
r
ep
r
esen
ts
th
e
o
r
ig
i
n
al
d
ata,
y
ello
w
r
ep
r
ese
n
ts
t
h
e
L
ST
M
m
o
d
el
p
r
ed
ictio
n
,
an
d
p
in
k
r
e
p
r
esen
ts
t
h
e
R
NN
m
o
d
el
p
r
ed
ictio
n
.
I
t
is
o
b
v
io
u
s
f
r
o
m
t
h
e
f
i
g
u
r
e
t
h
at
t
h
e
R
NN
m
o
d
el
p
r
ed
icts
b
etter
t
h
a
n
t
h
e
L
ST
M
m
o
d
el.
Fi
g
u
r
e
5
illu
s
t
r
ates
th
at
th
e
R
NN
m
o
d
el
h
as
b
etter
ac
c
u
r
ac
y
a
n
d
p
r
ed
ictio
n
p
er
f
o
r
m
a
n
ce
.
A
s
ca
n
b
e
s
ee
n
f
r
o
m
Fi
g
u
r
e
6
,
b
lu
e
r
ep
r
esen
ts
th
e
o
r
ig
in
al
d
ata,
y
el
lo
w
r
ep
r
esen
t
s
th
e
L
ST
M
m
o
d
el
p
r
ed
ictio
n
,
an
d
g
r
ee
n
r
ep
r
esen
ts
th
e
R
N
N
m
o
d
el
p
r
ed
ictio
n
.
I
t is o
b
v
io
u
s
f
r
o
m
t
h
e
f
i
g
u
r
e
th
at
th
e
R
N
N
m
o
d
el
p
r
ed
icts
b
etter
th
an
t
h
e
L
ST
M
m
o
d
el.
Fig
u
r
e
4
.
C
o
m
p
ar
e
R
NN
m
o
d
el
an
d
L
ST
M
m
o
d
el
p
er
f
o
r
m
a
n
ce
in
d
e
x
in
t
h
e
d
ataset
T
ab
le
5
.
C
o
m
p
ar
e
R
NN
m
o
d
e
l a
n
d
L
ST
M
m
o
d
el
p
er
f
o
r
m
an
ce
in
d
ex
i
n
th
e
m
er
g
ed
d
a
taset
(
lar
g
e
in
d
u
s
tr
ial
elec
tr
icit
y
a
v
er
ag
e
p
o
w
er
m
ax
)
M
o
d
e
l
R
M
S
E
M
A
E
M
S
E
S
A
R
I
M
A
X
1
1
8
6
9
.
7
2
8
4
5
2
.
0
4
1
4
0
8
9
0
2
1
8
L
S
T
M
0
.
0
6
8
7
1
0
.
0
4
9
8
6
0
.
0
0
4
7
R
N
N
0
.
0
6
5
0
7
0
.
0
4
9
7
4
8
0
.
0
0
4
2
As
ca
n
b
e
s
ee
n
i
n
T
ab
le
s
4
an
d
5
,
th
e
R
N
N
o
u
tp
er
f
o
r
m
e
d
b
o
th
L
ST
M,
AR
I
M
A
,
an
d
s
ea
s
o
n
a
l
au
to
r
eg
r
es
s
iv
e
in
teg
r
ated
m
o
v
in
g
a
v
er
ag
e
w
it
h
ex
p
la
n
ato
r
y
(
S
A
R
I
M
AX
)
.
T
h
e
r
ea
s
o
n
f
o
r
th
e
g
o
o
d
p
er
f
o
r
m
a
n
ce
o
f
R
N
N
co
u
ld
b
e
r
elate
d
to
th
e
n
at
u
r
e
o
f
t
h
e
d
atasets
t
h
e
m
s
el
v
es.
I
n
th
e
c
o
n
tex
t
o
f
r
eg
io
n
a
l
elec
tr
icit
y
lo
ad
f
o
r
ec
asti
n
g
,
it
u
s
es
h
ig
h
-
f
r
eq
u
e
n
c
y
d
ata
w
h
ic
h
is
r
ec
o
r
d
ed
at
1
5
-
m
i
n
u
te
i
n
ter
v
a
ls
.
T
h
e
f
o
r
ec
asti
n
g
p
er
f
o
r
m
an
ce
o
f
a
m
o
d
el
is
c
lo
s
el
y
li
n
k
ed
to
i
ts
ab
ilit
y
to
ca
p
tu
r
e
t
h
e
te
m
p
o
r
al
d
ep
en
d
en
cies
in
h
er
e
n
t
in
th
e
d
ata.
E
lectr
ici
t
y
d
e
m
an
d
i
s
u
s
u
all
y
c
h
ar
ac
t
er
ized
b
y
s
tr
o
n
g
lo
ca
l,
s
h
o
r
t
-
ter
m
d
ep
en
d
en
cie
s
,
w
h
er
e
t
h
e
lo
ad
v
al
u
es o
f
t
h
e
la
s
t f
e
w
h
o
u
r
s
h
av
e
a
g
r
ea
ter
i
n
f
lu
en
ce
o
n
f
u
tu
r
e
co
n
s
u
m
p
tio
n
th
an
th
e
lo
n
g
-
ter
m
h
is
to
r
ical
v
alu
e
s
.
R
N
Ns
ar
e
p
ar
ticu
lar
l
y
w
ell
s
u
ited
to
s
u
c
h
s
ce
n
ar
io
s
,
as
th
e
ir
ar
ch
itect
u
r
e
allo
w
s
in
f
o
r
m
at
io
n
to
b
e
p
ass
ed
s
eq
u
en
tiall
y
t
h
r
o
u
g
h
h
id
d
en
s
tates,
p
r
eser
v
i
n
g
th
e
i
m
m
ed
iate
co
n
te
x
t
o
f
t
h
e
p
ast
w
it
h
o
u
t
m
a
k
i
n
g
th
e
m
o
d
el
u
n
n
ec
es
s
ar
il
y
co
m
p
lex
.
I
n
co
n
tr
ast
to
L
ST
M
n
et
w
o
r
k
s
,
w
h
ic
h
ar
e
d
esig
n
ed
to
ca
p
tu
r
e
lo
n
g
-
ter
m
d
ep
en
d
en
ci
es
th
r
o
u
g
h
g
ati
n
g
m
ec
h
an
i
s
m
s
a
n
d
m
e
m
o
r
y
ce
lls
,
R
NN
s
ef
f
ec
ti
v
e
l
y
ca
p
tu
r
e
s
h
o
r
t
-
ter
m
p
atter
n
s
t
h
at
d
o
m
i
n
ate
h
ig
h
-
f
r
eq
u
en
c
y
lo
ad
f
o
r
ec
asts
.
I
n
ad
d
itio
n
,
th
e
r
elativ
el
y
s
m
all
n
u
m
b
er
o
f
attr
ib
u
te
s
in
t
h
e
d
atasets
,
in
cl
u
d
in
g
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
R
ec
o
n
f
i
g
u
r
ab
le
&
E
m
b
ed
d
ed
Sy
s
t
I
SS
N:
2089
-
4864
I
n
ve
s
tig
a
tin
g
th
e
p
erfo
r
ma
n
ce
o
f R
N
N
mo
d
el
to
fo
r
ec
a
s
t th
e
elec
tr
icity
p
o
w
er
…
(
Ha
n
Min
g
yin
g
)
503
elec
tr
ical
lo
ad
,
in
d
u
s
tr
ial
co
n
s
u
m
p
tio
n
an
d
m
eteo
r
o
lo
g
ical
v
ar
iab
les,
h
en
ce
f
u
r
th
er
r
ed
u
ce
s
th
e
n
ee
d
f
o
r
co
m
p
le
x
s
to
r
ag
e
ar
ch
i
tectu
r
e
s
.
E
x
ter
n
al
f
ac
to
r
s
s
u
c
h
as
t
e
m
p
er
atu
r
e
an
d
w
in
d
s
p
ee
d
t
y
p
icall
y
h
a
v
e
an
i
m
m
ed
iate
i
m
p
ac
t
o
n
elec
tr
icity
d
e
m
an
d
,
h
i
g
h
l
ig
h
ti
n
g
th
e
s
u
i
tab
ilit
y
o
f
R
NN
s
th
at
ca
n
ef
f
ic
ien
tl
y
m
o
d
el
th
es
e
s
h
o
r
t
-
ter
m
ca
u
s
e
-
a
n
d
-
e
f
f
ec
t
r
elatio
n
s
h
ip
s
.
T
h
e
s
u
p
er
io
r
p
er
f
o
r
m
a
n
ce
o
f
R
NNs
i
n
th
is
co
n
t
ex
t
ca
n
th
er
ef
o
r
e
b
e
attr
ib
u
ted
to
th
e
m
a
tch
b
et
wee
n
th
e
m
o
d
el’
s
ab
ilit
y
to
ca
p
tu
r
e
lo
ca
l
d
ep
en
d
en
cies
a
n
d
th
e
s
h
o
r
t
-
ter
m
,
h
ig
h
-
f
r
eq
u
en
c
y
n
atu
r
e
o
f
t
h
e
l
o
ad
f
o
r
ec
ast d
ata.
Fig
u
r
e
5
.
C
o
m
p
ar
e
R
NN
m
o
d
el
an
d
L
ST
M
m
o
d
el
in
t
h
e
1
5
-
m
i
n
u
te
i
n
ter
v
als
Fig
u
r
e
6
.
C
o
m
p
ar
e
R
NN
m
o
d
el
an
d
L
ST
M
m
o
d
el
in
t
h
e
m
e
r
g
ed
d
ataset
(
lar
g
e
in
d
u
s
tr
ial
e
lectr
icit
y
a
v
er
ag
e
p
o
w
er
m
a
x
)
Fig
u
r
e
7
is
t
h
e
u
s
e
o
f
R
N
N
m
o
d
el
to
p
r
ed
ict
th
e
u
s
a
g
e
o
f
el
ec
tr
icit
y
lo
ad
at
1
5
m
i
n
u
tes
ap
ar
t
o
v
er
1
0
d
ay
s
.
A
s
ca
n
b
e
s
ee
n
f
r
o
m
t
h
e
f
ig
u
r
e,
th
e
p
o
w
er
u
s
e
ar
ea
i
s
f
r
o
m
lo
w
to
h
i
g
h
an
d
g
r
ad
u
a
ll
y
ten
d
s
to
a
s
tab
le
v
alu
e.
F
ig
u
r
e
8
is
th
e
u
s
e
o
f
R
NN
m
o
d
el
to
p
r
ed
ict
th
e
u
s
a
g
e
o
f
elec
tr
ic
it
y
lo
ad
w
it
h
i
n
3
0
d
ay
s
in
t
h
e
m
er
g
ed
d
ataset.
T
h
e
av
er
ag
e
m
a
x
i
m
u
m
p
o
w
er
co
n
s
u
m
p
tio
n
o
f
lar
g
e
i
n
d
u
s
tr
ies
p
r
ed
icted
u
s
i
n
g
th
e
R
NN
m
o
d
el
i
s
ab
o
v
e
1
2
,
0
0
0
an
d
th
e
av
er
ag
e
m
i
n
i
m
u
m
p
o
w
er
co
n
s
u
m
p
tio
n
is
w
ith
in
t
h
e
r
an
g
e
o
f
9
0
,
0
0
0
an
d
9
5
,
0
0
0
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
9
-
4864
I
n
t J
R
ec
o
n
f
i
g
u
r
ab
le
&
E
m
b
ed
d
ed
Sy
s
t
,
Vo
l.
14
,
No
.
2
,
J
u
l
y
20
25
:
497
-
5
0
6
504
Fig
u
r
e
7
.
Usi
n
g
R
N
N
m
o
d
el
f
o
r
f
u
t
u
r
e
1
0
d
ay
s
i
n
th
e
1
5
-
m
i
n
u
te
i
n
ter
v
als r
e
g
io
n
al
p
o
w
er
lo
ad
d
ataset
Fig
u
r
e
8
.
Usi
n
g
R
N
N
m
o
d
el
f
o
r
3
0
d
ay
s
i
n
t
h
e
m
er
g
ed
d
ataset
(
lar
g
e
in
d
u
s
tr
ial
elec
tr
icit
y
)
4.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
i
n
v
e
s
ti
g
ates
t
h
e
p
er
f
o
r
m
an
ce
o
f
d
ee
p
lear
n
in
g
m
o
d
els
o
n
t
w
o
d
if
f
er
e
n
ce
d
atas
et,
n
a
m
el
y
d
ataset
an
d
m
er
g
ed
d
ataset
b
y
u
s
i
n
g
th
r
ee
m
o
d
els,
AR
I
M
A
,
L
ST
M
,
an
d
R
NN.
Data
s
et
is
f
ea
tu
r
ed
b
y
th
e
in
d
ex
i
n
g
o
f
d
ate
ti
m
e,
a
s
in
g
l
e
in
p
u
t
v
ar
iab
le
th
at
is
th
e
v
al
u
e
o
f
elec
tr
icit
y
co
n
s
u
m
p
tio
n
,
an
d
a
s
in
g
le
tar
g
e
t
v
ar
iab
le
th
a
t
is
a
s
i
n
g
le
p
r
ed
icted
v
alu
e.
T
h
e
m
er
g
ed
d
ata
s
et
is
f
ea
tu
r
ed
b
y
th
e
p
r
esen
ce
o
f
ex
ter
n
a
l
v
ar
iab
le
s
to
ex
p
lo
r
e
th
e
ef
f
ec
t
o
f
te
m
p
er
atu
r
e
f
ac
to
r
s
o
n
elec
tr
icit
y
co
n
s
u
m
p
tio
n
lo
ad
.
T
h
er
ef
o
r
e,
th
e
S
A
R
I
M
A
X
m
o
d
el
is
r
eq
u
ir
ed
to
an
al
y
ze
t
h
e
e
x
ter
n
al
v
ar
i
ab
les.
A
cc
o
r
d
in
g
to
th
e
ch
ar
ac
ter
is
t
ics
o
f
d
a
taset,
f
o
u
r
m
o
d
els,
AR
I
M
A
,
S
A
R
I
M
A
X,
L
ST
M,
an
d
R
NN
m
o
d
els
w
er
e
ap
p
lied
an
d
ev
alu
ated
o
n
d
if
f
er
en
t
d
atasets
,
d
em
o
n
s
tr
ati
n
g
th
eir
ad
v
an
ta
g
e
s
an
d
d
is
ad
v
an
ta
g
es.
R
NN
co
n
s
i
s
te
n
tl
y
o
u
tp
er
f
o
r
m
s
L
ST
M,
d
em
o
n
s
tr
atin
g
its
s
u
p
er
io
r
it
y
i
n
ac
cu
r
ac
y
a
n
d
p
r
ed
ictiv
e
p
er
f
o
r
m
an
ce
.
U
s
i
n
g
R
NN
f
o
r
s
h
o
r
t
-
ter
m
an
d
lo
n
g
-
ter
m
f
o
r
ec
asti
n
g
d
em
o
n
s
tr
ate
s
its
p
o
ten
tia
l
ap
p
licab
ilit
y
i
n
f
o
r
ec
asti
n
g
elec
tr
icit
y
lo
ad
s
.
H
y
p
er
p
ar
a
m
eter
tu
n
i
n
g
i
s
a
k
e
y
s
tep
in
th
is
r
esear
ch
p
r
o
j
ec
t.
I
t
f
in
d
s
th
e
o
p
ti
m
al
v
al
u
es
o
f
th
e
m
o
d
el
h
y
p
er
p
ar
a
m
eter
s
to
m
a
x
i
m
i
ze
its
p
er
f
o
r
m
a
n
ce
an
d
p
r
ed
ictio
n
ac
cu
r
ac
y
.
T
h
is
s
tu
d
y
e
m
p
lo
y
ed
a
g
r
id
s
ea
r
c
h
tech
n
iq
u
e
f
o
r
h
y
p
er
p
ar
a
m
et
er
tu
n
i
n
g
,
w
h
er
e
a
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
R
ec
o
n
f
i
g
u
r
ab
le
&
E
m
b
ed
d
ed
Sy
s
t
I
SS
N:
2089
-
4864
I
n
ve
s
tig
a
tin
g
th
e
p
erfo
r
ma
n
ce
o
f R
N
N
mo
d
el
to
fo
r
ec
a
s
t th
e
elec
tr
icity
p
o
w
er
…
(
Ha
n
Min
g
yin
g
)
505
g
r
id
o
f
h
y
p
er
p
ar
a
m
eter
v
a
lu
e
s
is
d
ef
i
n
ed
an
d
th
e
m
o
d
el
i
s
tr
ain
ed
an
d
ev
alu
a
ted
f
o
r
ea
ch
co
m
b
in
a
tio
n
o
f
v
alu
e
s
.
T
h
is
ex
h
a
u
s
t
iv
e
s
ea
r
c
h
ev
al
u
ates
th
e
m
o
d
el
's
p
er
f
o
r
m
an
ce
u
n
d
er
d
if
f
er
e
n
t
h
y
p
er
p
ar
am
eter
s
etti
n
g
s
an
d
d
eter
m
in
e
s
th
e
o
p
ti
m
al
co
n
f
ig
u
r
atio
n
.
D
u
r
in
g
th
e
h
y
p
er
p
ar
am
eter
t
u
n
i
n
g
p
r
o
ce
s
s
,
ev
al
u
atio
n
m
etr
ics
s
u
c
h
as
MSE
,
M
A
E
,
R
MSE
,
an
d
R
²
to
ass
e
s
s
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
m
o
d
el.
B
y
co
m
p
ar
i
n
g
t
h
e
p
er
f
o
r
m
a
n
ce
m
etr
ics
o
f
d
i
f
f
er
e
n
t
h
y
p
er
p
ar
a
m
eter
co
m
b
i
n
atio
n
s
,
it
c
an
b
e
ab
le
to
d
eter
m
i
n
e
t
h
e
o
p
ti
m
al
s
et
o
f
h
y
p
er
p
ar
a
m
eter
s
t
h
at
p
r
o
d
u
ce
d
th
e
b
est
r
esu
lts
.
T
h
is
lea
d
s
to
im
p
r
o
v
ed
m
o
d
el
p
er
f
o
r
m
an
c
e
an
d
b
etter
p
r
ed
ictio
n
s
.
B
y
ca
r
ef
u
ll
y
t
u
n
i
n
g
th
e
h
y
p
er
p
ar
am
e
ter
s
,
it
ca
n
i
m
p
r
o
v
e
t
h
e
ac
cu
r
ac
y
a
n
d
ef
f
ec
tiv
e
n
e
s
s
o
f
t
h
e
m
o
d
el
in
p
r
ed
icti
n
g
p
o
w
er
l
o
ad
d
ata
an
d
s
u
p
p
o
r
tin
g
d
ec
is
io
n
-
m
ak
i
n
g
i
n
t
h
e
g
r
id
in
d
u
s
tr
y
.
Fo
r
f
u
t
u
r
e
r
ec
o
m
m
e
n
d
atio
n
s
,
w
e
w
o
u
ld
lik
e
to
ex
p
lo
r
e
h
y
b
r
id
m
o
d
elin
g
ap
p
r
o
ac
h
es
f
o
r
elec
tr
icit
y
co
n
s
u
m
p
tio
n
f
o
r
ec
asti
n
g
,
b
y
co
m
b
in
in
g
t
h
e
s
tr
e
n
g
t
h
s
o
f
d
i
f
f
er
e
n
t
m
o
d
elin
g
tec
h
n
iq
u
e
s
,
s
u
ch
a
s
s
tatis
tical,
m
ac
h
in
e
lear
n
in
g
,
an
d
d
ee
p
lear
n
in
g
m
o
d
els
to
i
m
p
r
o
v
e
p
r
ed
ict
io
n
ac
cu
r
ac
y
an
d
r
o
b
u
s
tn
es
s
.
I
n
ad
d
itio
n
,
th
e
T
r
an
s
f
o
r
m
er
m
o
d
els,
a
ls
o
ca
n
b
e
ta
k
en
in
to
co
n
s
id
er
atio
n
,
as
i
t
h
a
s
t
h
e
ab
ilit
y
to
c
ap
tu
r
e
lo
n
g
-
r
a
n
g
e
d
ep
en
d
en
cies
an
d
co
m
p
le
x
t
e
m
p
o
r
al
p
atter
n
s
.
T
h
is
w
i
ll
o
f
f
er
s
ig
n
i
f
ica
n
t
p
o
ten
tial
i
n
m
o
d
eli
n
g
elec
tr
icit
y
u
s
a
g
e
tr
en
d
s
,
esp
ec
iall
y
in
s
c
en
ar
io
s
w
i
t
h
h
i
g
h
v
ar
iab
ilit
y
o
r
n
o
n
-
li
n
ea
r
it
y
.
T
h
ese
ap
p
r
o
ac
h
es
m
a
y
p
r
o
v
id
e
m
o
r
e
ac
c
u
r
ate
an
d
g
e
n
er
aliza
b
le
f
o
r
ec
asts
,
s
u
p
p
o
r
tin
g
b
etter
en
er
g
y
m
a
n
a
g
e
m
en
t a
n
d
p
lan
n
in
g
d
ec
i
s
io
n
s
.
RE
F
E
R
E
NC
E
S
[
1
]
M
.
Y
a
n
g
,
D
.
P
a
t
i
ñ
o
-
Ec
h
e
v
e
r
r
i
,
F
.
Y
a
n
g
,
a
n
d
E.
W
i
l
l
i
a
ms,
“
I
n
d
u
st
r
i
a
l
e
n
e
r
g
y
e
f
f
i
c
i
e
n
c
y
i
n
C
h
i
n
a
:
a
c
h
i
e
v
e
me
n
t
s,
c
h
a
l
l
e
n
g
e
s
a
n
d
o
p
p
o
r
t
u
n
i
t
i
e
s,”
E
n
e
rg
y
S
t
r
a
t
e
g
y
R
e
v
i
e
w
s
,
v
o
l
.
6
,
p
p
.
2
0
–
2
9
,
Ja
n
.
2
0
1
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sr
.
2
0
1
4
.
1
1
.
0
0
7
.
[
2
]
R
.
B
a
n
i
k
,
P
.
D
a
s
,
S
.
R
a
y
,
a
n
d
A
.
B
i
sw
a
s,
“
P
r
e
d
i
c
t
i
o
n
o
f
e
l
e
c
t
r
i
c
a
l
e
n
e
r
g
y
c
o
n
su
mp
t
i
o
n
b
a
se
d
o
n
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
,
”
El
e
c
t
r
i
c
a
l
En
g
i
n
e
e
r
i
n
g
,
v
o
l
.
1
0
3
,
n
o
.
2
,
p
p
.
9
0
9
–
9
2
0
,
A
p
r
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s
0
0
2
0
2
-
0
2
0
-
0
1
1
2
6
-
z
.
[
3
]
Á
.
C
a
sa
d
o
a
n
d
J.
H
e
r
a
s,
“
G
u
i
d
i
n
g
t
h
e
c
r
e
a
t
i
o
n
o
f
d
e
e
p
l
e
a
r
n
i
n
g
-
b
a
se
d
o
b
j
e
c
t
d
e
t
e
c
t
o
r
s,”
a
r
Xi
v
,
2
0
1
8
,
d
o
i
:
1
0
.
4
8
5
5
0
/
a
r
X
i
v
.
1
8
0
9
.
0
3
3
2
2
[
4
]
P
.
D
u
,
J.
W
a
n
g
,
W
.
Y
a
n
g
,
a
n
d
T
.
N
i
u
,
“
M
u
l
t
i
-
st
e
p
a
h
e
a
d
f
o
r
e
c
a
st
i
n
g
i
n
e
l
e
c
t
r
i
c
a
l
p
o
w
e
r
s
y
st
e
m
u
si
n
g
a
h
y
b
r
i
d
f
o
r
e
c
a
st
i
n
g
sy
st
e
m,”
Re
n
e
w
a
b
l
e
E
n
e
r
g
y
,
v
o
l
.
1
2
2
,
p
p
.
5
3
3
–
5
5
0
,
A
p
r
.
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
r
e
n
e
n
e
.
2
0
1
8
.
0
1
.
1
1
3
.
[
5
]
A
.
A
z
e
e
m,
I
.
I
smai
l
,
S
.
M
.
Jame
e
l
,
a
n
d
V
.
R
.
H
a
r
i
n
d
r
a
n
,
“
El
e
c
t
r
i
c
a
l
l
o
a
d
f
o
r
e
c
a
st
i
n
g
mo
d
e
l
s
f
o
r
d
i
f
f
e
r
e
n
t
g
e
n
e
r
a
t
i
o
n
mo
d
a
l
i
t
i
e
s:
a
r
e
v
i
e
w
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
9
,
p
p
.
1
4
2
2
3
9
–
1
4
2
2
6
3
,
O
c
t
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
1
.
3
1
2
0
7
3
1
.
[
6
]
Y
.
D
o
n
g
,
X
.
M
a
,
a
n
d
T
.
F
u
,
“
El
e
c
t
r
i
c
a
l
l
o
a
d
f
o
r
e
c
a
st
i
n
g
:
A
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
b
a
se
d
o
n
K
-
n
e
a
r
e
st
n
e
i
g
h
b
o
r
s,”
A
p
p
l
i
e
d
S
o
f
t
C
o
m
p
u
t
i
n
g
,
v
o
l
.
9
9
,
p
p
.
1
0
6
9
0
0
,
D
e
c
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
so
c
.
2
0
2
0
.
1
0
6
9
0
0
.
[
7
]
M
.
I
man
i
,
“
El
e
c
t
r
i
c
a
l
l
o
a
d
-
t
e
m
p
e
r
a
t
u
r
e
C
N
N
f
o
r
r
e
si
d
e
n
t
i
a
l
l
o
a
d
f
o
r
e
c
a
st
i
n
g
,
”
En
e
rg
y
,
v
o
l
.
2
2
7
,
p
p
.
1
2
0
4
8
0
,
D
e
c
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
e
r
g
y
.
2
0
2
1
.
1
2
0
4
8
0
.
[
8
]
A
.
D
i
P
i
a
z
z
a
,
M
.
C
.
D
i
P
i
a
z
z
a
,
G
.
L
a
T
o
n
a
,
a
n
d
M
.
L
u
n
a
,
“
A
n
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
-
b
a
se
d
f
o
r
e
c
a
st
i
n
g
mo
d
e
l
o
f
e
n
e
r
g
y
-
r
e
l
a
t
e
d
t
i
me
se
r
i
e
s
f
o
r
e
l
e
c
t
r
i
c
a
l
g
r
i
d
ma
n
a
g
e
me
n
t
,
”
M
a
t
h
e
m
a
t
i
c
s
a
n
d
C
o
m
p
u
t
e
rs
i
n
S
i
m
u
l
a
t
i
o
n
,
v
o
l
.
1
8
4
,
p
p
.
2
9
4
–
3
0
5
,
D
e
c
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
ma
t
c
o
m.
2
0
2
0
.
0
5
.
0
1
0
.
[
9
]
Á
.
C
a
sa
d
o
a
n
d
J.
H
e
r
a
s,
“
G
u
i
d
i
n
g
t
h
e
c
r
e
a
t
i
o
n
o
f
d
e
e
p
l
e
a
r
n
i
n
g
-
b
a
se
d
o
b
j
e
c
t
d
e
t
e
c
t
o
r
s,”
a
r
Xi
v
,
2
0
1
8
,
d
o
i
:
1
0
.
4
8
5
5
0
/
a
r
X
i
v
.
1
8
0
9
.
0
3
3
2
2
.
[
1
0
]
M
.
A
.
H
a
mm
a
d
,
B
.
Je
r
e
b
,
B
.
R
o
si
,
a
n
d
D
.
D
r
a
g
a
n
,
“
M
e
t
h
o
d
s
a
n
d
M
o
d
e
l
s
f
o
r
E
l
e
c
t
r
i
c
L
o
a
d
F
o
r
e
c
a
st
i
n
g
:
A
C
o
m
p
r
e
h
e
n
si
v
e
R
e
v
i
e
w
,
”
L
o
g
i
s
t
i
c
s,
S
u
p
p
l
y
C
h
a
i
n
,
S
u
st
a
i
n
a
b
i
l
i
t
y
a
n
d
G
l
o
b
a
l
C
h
a
l
l
e
n
g
e
s
,
v
o
l
.
1
1
,
n
o
.
1
,
p
p
.
5
1
–
7
6
,
2
0
2
0
,
d
o
i
:
1
0
.
2
4
7
8
/
j
l
st
-
2
0
2
0
-
0
0
0
4
.
[
1
1
]
I
.
G
u
p
t
a
a
n
d
G
.
N
a
g
p
a
l
,
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
Ex
p
e
r
t
S
y
s
t
e
m
s
,
M
e
r
c
u
r
y
L
e
a
r
n
i
n
g
a
n
d
I
n
f
o
r
mat
i
o
n
,
2
0
2
0
,
d
o
i
:
1
0
.
1
5
1
5
/
9
7
8
1
6
8
3
9
2
5
0
5
7
.
[
1
2
]
S
.
R
a
i
a
n
d
M
.
D
e
,
“
A
n
a
l
y
si
s
o
f
c
l
a
ss
i
c
a
l
a
n
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
b
a
se
d
s
h
o
r
t
-
t
e
r
m
a
n
d
mi
d
-
t
e
r
m
l
o
a
d
f
o
r
e
c
a
st
i
n
g
f
o
r
smar
t
g
r
i
d
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
S
u
s
t
a
i
n
a
b
l
e
En
e
r
g
y
,
p
p
.
1
–
1
9
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
8
0
/
1
4
7
8
6
4
5
1
.
2
0
2
1
.
1
8
7
3
3
3
9
.
[
1
3
]
W.
-
J.
L
e
e
a
n
d
J.
H
o
n
g
,
“
A
h
y
b
r
i
d
d
y
n
a
mi
c
a
n
d
f
u
z
z
y
t
i
me
se
r
i
e
s
mo
d
e
l
f
o
r
mi
d
-
t
e
r
m
p
o
w
e
r
l
o
a
d
f
o
r
e
c
a
st
i
n
g
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
t
r
i
c
a
l
P
o
w
e
r
a
n
d
En
e
r
g
y
S
y
st
e
m
s
,
v
o
l
.
6
4
,
p
p
.
1
0
5
7
–
1
0
6
2
,
D
e
c
.
2
0
1
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
j
e
p
e
s.2
0
1
4
.
0
8
.
0
0
6
.
[
1
4
]
M
.
S
a
r
st
e
d
t
a
n
d
E.
M
o
o
i
,
“
R
e
g
r
e
ssi
o
n
a
n
a
l
y
si
s
,”
A
C
o
n
c
i
s
e
G
u
i
d
e
t
o
M
a
r
k
e
t
R
e
se
a
rc
h
,
p
p
.
2
0
9
–
2
5
6
,
2
0
1
8
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
6
6
2
-
5
6
7
0
7
-
4
_
7
.
[
1
5
]
D
.
C
.
M
o
n
t
g
o
me
r
y
,
C
.
L
.
J
e
n
n
i
n
g
s,
a
n
d
M
.
K
u
l
a
h
c
i
,
I
n
t
r
o
d
u
c
t
i
o
n
t
o
T
i
m
e
S
e
r
i
e
s
An
a
l
y
si
s
a
n
d
F
o
rec
a
s
t
i
n
g
,
2
n
d
e
d
.
,
W
i
l
e
y
,
H
o
b
o
k
e
n
,
N
J,
2
0
1
6
,
d
o
i
:
1
0
.
1
1
1
1
/
j
t
sa.
1
2
2
0
3
.
[
1
6
]
M
.
S
.
S
.
R
a
o
,
S
.
A
.
S
o
man
,
B
.
L
.
M
e
n
e
z
e
s,
P
.
C
h
a
w
a
n
d
e
,
D
.
P
.
,
a
n
d
G
.
T
.
,
“
A
n
e
x
p
e
r
t
sy
st
e
m
a
p
p
r
o
a
c
h
t
o
sh
o
r
t
-
t
e
r
m
l
o
a
d
f
o
r
e
c
a
st
i
n
g
f
o
r
R
e
l
i
a
n
c
e
E
n
e
r
g
y
L
i
mi
t
e
d
,
M
u
m
b
a
i
,
”
2
0
0
6
I
EEE
P
o
w
e
r
I
n
d
i
a
C
o
n
f
e
re
n
c
e
,
2
0
0
6
,
d
o
i
:
1
0
.
1
1
0
9
/
p
o
w
e
r
i
.
2
0
0
6
.
1
6
3
2
6
0
4
.
[
1
7
]
P.
-
H
.
K
u
o
a
n
d
C
.
-
J
.
H
u
a
n
g
,
“
A
h
i
g
h
p
r
e
c
i
si
o
n
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s
m
o
d
e
l
f
o
r
sh
o
r
t
-
t
e
r
m
e
n
e
r
g
y
l
o
a
d
f
o
r
e
c
a
st
i
n
g
,
”
E
n
e
r
g
i
e
s
,
v
o
l
.
1
1
,
n
o
.
1
,
p
p
.
2
1
3
,
2
0
1
8
,
d
o
i
:
1
0
.
3
3
9
0
/
e
n
1
1
0
1
0
2
1
3
.
[
1
8
]
T
.
L
e
e
t
a
l
.
,
“
I
mp
r
o
v
i
n
g
e
l
e
c
t
r
i
c
e
n
e
r
g
y
c
o
n
su
m
p
t
i
o
n
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
C
N
N
a
n
d
B
i
-
L
S
T
M
,
”
Ap
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
9
,
n
o
.
2
0
,
p
p
.
4
2
3
7
,
2
0
1
9
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
9
2
0
4
2
3
7
.
[
1
9
]
W
.
C
h
a
r
y
t
o
n
i
u
k
a
n
d
M
.
-
S
.
C
h
e
n
,
“
V
e
r
y
sh
o
r
t
-
t
e
r
m
l
o
a
d
f
o
r
e
c
a
st
i
n
g
u
si
n
g
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s,”
I
E
EE
T
ra
n
s
a
c
t
i
o
n
s
o
n
Po
w
e
r
S
y
s
t
e
m
s
,
v
o
l
.
1
5
,
n
o
.
1
,
p
p
.
2
6
3
–
2
6
8
,
F
e
b
.
2
0
0
0
,
d
o
i
:
1
0
.
1
1
0
9
/
5
9
.
8
5
2
1
3
1
.
[
2
0
]
J.
Y
a
n
g
,
G
.
L
i
u
,
J
.
Z
h
a
o
,
F
.
W
e
n
,
a
n
d
C
.
D
o
n
g
,
“
A
l
o
n
g
sh
o
r
t
t
e
r
m
me
mo
r
y
b
a
se
d
d
e
e
p
l
e
a
r
n
i
n
g
me
t
h
o
d
f
o
r
i
n
d
u
st
r
i
a
l
l
o
a
d
f
o
r
e
c
a
st
i
n
g
,
”
J
o
u
rn
a
l
N
a
v
i
g
a
t
i
o
n
,
p
p
.
2
0
–
2
7
,
2
0
1
8
,
d
o
i
:
1
0
.
3
9
6
9
/
j
.
i
ss
n
.
1
0
0
0
-
7
2
2
9
.
2
0
1
8
.
1
0
.
0
0
3
.
[
2
1
]
S
.
B
o
u
k
t
i
f
,
A
.
F
i
a
z
,
A
.
O
u
n
i
,
a
n
d
M
.
S
e
r
h
a
n
i
,
“
O
p
t
i
mal
d
e
e
p
l
e
a
r
n
i
n
g
L
S
T
M
mo
d
e
l
f
o
r
e
l
e
c
t
r
i
c
l
o
a
d
f
o
r
e
c
a
st
i
n
g
u
si
n
g
f
e
a
t
u
r
e
se
l
e
c
t
i
o
n
a
n
d
g
e
n
e
t
i
c
a
l
g
o
r
i
t
h
m:
c
o
m
p
a
r
i
so
n
w
i
t
h
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
e
s
,
”
E
n
e
r
g
i
e
s
,
v
o
l
.
1
1
,
n
o
.
7
,
p
p
.
1
6
3
6
,
2
0
1
8
,
d
o
i
:
1
0
.
3
3
9
0
/
e
n
1
1
0
7
1
6
3
6
.
[
2
2
]
S
.
G
.
N
a
n
d
G
.
S
.
S
h
e
sh
a
d
r
i
,
“
El
e
c
t
r
i
c
a
l
l
o
a
d
f
o
r
e
c
a
st
i
n
g
u
si
n
g
t
i
me
se
r
i
e
s
a
n
a
l
y
si
s
,”
2
0
2
0
I
EEE
B
a
n
g
a
l
o
r
e
H
u
m
a
n
i
t
a
r
i
a
n
T
e
c
h
n
o
l
o
g
y
C
o
n
f
e
re
n
c
e
(
B
-
H
T
C
)
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
b
-
h
t
c
5
0
9
7
0
.
2
0
2
0
.
9
2
9
7
9
8
6
.
[
2
3
]
M
.
G
a
o
,
J.
L
i
,
F
.
H
o
n
g
,
a
n
d
D
.
L
o
n
g
,
“
D
a
y
-
a
h
e
a
d
p
o
w
e
r
f
o
r
e
c
a
st
i
n
g
i
n
a
l
a
r
g
e
-
sca
l
e
p
h
o
t
o
v
o
l
t
a
i
c
p
l
a
n
t
b
a
se
d
o
n
w
e
a
t
h
e
r
c
l
a
ssi
f
i
c
a
t
i
o
n
u
s
i
n
g
L
S
T
M
,
”
E
n
e
r
g
y
,
v
o
l
.
1
8
7
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
e
r
g
y
.
2
0
1
9
.
0
7
.
1
6
8
.
[
2
4
]
Z
.
G
u
o
,
K
.
Z
h
o
u
,
X
.
Z
h
a
n
g
,
a
n
d
S
.
Y
a
n
g
,
“
A
d
e
e
p
l
e
a
r
n
i
n
g
mo
d
e
l
f
o
r
sh
o
r
t
-
t
e
r
m
p
o
w
e
r
l
o
a
d
a
n
d
p
r
o
b
a
b
i
l
i
t
y
d
e
n
si
t
y
f
o
r
e
c
a
st
i
n
g
,
”
En
e
r
g
y
,
v
o
l
.
1
6
0
,
p
p
.
1
1
8
6
–
1
2
0
0
,
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
e
r
g
y
.
2
0
1
8
.
0
7
.
0
9
0
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
9
-
4864
I
n
t J
R
ec
o
n
f
i
g
u
r
ab
le
&
E
m
b
ed
d
ed
Sy
s
t
,
Vo
l.
14
,
No
.
2
,
J
u
l
y
20
25
:
497
-
5
0
6
506
[
2
5
]
W.
-
J.
L
e
e
a
n
d
J.
H
o
n
g
,
“
A
h
y
b
r
i
d
d
y
n
a
mi
c
a
n
d
f
u
z
z
y
t
i
me
se
r
i
e
s
mo
d
e
l
f
o
r
mi
d
-
t
e
r
m
p
o
w
e
r
l
o
a
d
f
o
r
e
c
a
st
i
n
g
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
t
r
i
c
a
l
P
o
w
e
r
a
n
d
En
e
r
g
y
S
y
st
e
m
s
,
v
o
l
.
6
4
,
p
p
.
1
0
5
7
–
1
0
6
2
,
D
e
c
.
2
0
1
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
j
e
p
e
s.2
0
1
4
.
0
8
.
0
0
6
.
[
2
6
]
W
.
Z
h
a
n
g
,
J.
Q
i
n
,
F
.
M
e
i
,
J
.
F
u
,
B
.
D
a
i
,
a
n
d
W
.
Y
u
,
“
S
h
o
r
t
-
t
e
r
m
p
o
w
e
r
l
o
a
d
f
o
r
e
c
a
st
i
n
g
u
si
n
g
i
n
t
e
g
r
a
t
e
d
me
t
h
o
d
s
b
a
se
d
o
n
l
o
n
g
sh
o
r
t
-
t
e
r
m me
mo
r
y
,
”
S
c
i
e
n
c
e
C
h
i
n
a
T
e
c
h
n
o
l
o
g
i
c
a
l
S
c
i
e
n
c
e
s
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
4
3
1
-
0
1
9
-
9
5
4
7
-
4.
[
2
7
]
A
.
A
r
i
f
,
Z
.
W
a
n
g
,
J.
W
a
n
g
,
B
.
M
a
t
h
e
r
,
H
.
B
a
sh
u
a
l
d
o
,
a
n
d
D
.
Z
h
a
o
,
“
L
o
a
d
mo
d
e
l
i
n
g
–
a
r
e
v
i
e
w
,”
I
EEE
T
ra
n
s
a
c
t
i
o
n
s
o
n
S
m
a
rt
G
ri
d
,
,
v
o
l
.
1
,
p
p
.
1
–
1
,
2
0
1
7
,
d
o
i
:
1
0
.
1
1
0
9
/
t
sg
.
2
0
1
7
.
2
7
0
0
4
3
6
.
[
2
8
]
V
.
E.
S
a
t
h
i
s
h
k
u
m
a
r
e
t
a
l
.
,
“
A
n
e
n
e
r
g
y
c
o
n
su
m
p
t
i
o
n
p
r
e
d
i
c
t
i
o
n
mo
d
e
l
f
o
r
smar
t
f
a
c
t
o
r
y
u
si
n
g
d
a
t
a
m
i
n
i
n
g
a
l
g
o
r
i
t
h
ms,
”
K
I
P
S
T
ra
n
s
a
c
t
i
o
n
s
o
n
S
o
f
t
w
a
r
e
a
n
d
D
a
t
a
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
9
,
n
o
.
5
,
p
p
.
1
5
3
–
1
6
0
,
2
0
2
0
,
d
o
i
:
1
0
.
3
7
4
5
/
K
T
S
D
E.
2
0
2
0
.
9
.
5
.
1
5
3
.
[
2
9
]
A
.
B
h
a
n
d
a
r
y
e
t
a
l
.
,
“
En
h
a
n
c
i
n
g
h
o
u
s
e
h
o
l
d
e
n
e
r
g
y
c
o
n
su
mp
t
i
o
n
p
r
e
d
i
c
t
i
o
n
s
t
h
r
o
u
g
h
e
x
p
l
a
i
n
a
b
l
e
A
I
f
r
a
mew
o
r
k
s
,”
I
EEE
A
c
c
e
ss
,
v
o
l
.
1
2
,
p
p
.
3
6
7
6
4
-
3
6
7
7
7
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
4
.
3
3
7
3
5
5
2
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
H
a
n
M
in
g
y
in
g
re
c
e
iv
e
d
h
e
r
Ba
c
h
e
lo
r'
s
d
e
g
re
e
in
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
lo
g
y
f
ro
m
Zh
e
n
g
z
h
o
u
I
n
st
it
u
te
o
f
A
e
ro
n
a
u
ti
c
a
l
In
d
u
stry
M
a
n
a
g
e
m
e
n
t
in
2
0
1
8
.
S
h
e
h
a
s
w
o
rk
e
d
in
p
o
w
e
r
s
y
ste
m
p
ro
jec
t
m
a
n
a
g
e
m
e
n
t
f
ro
m
2
0
1
8
to
2
0
2
1
.
Cu
rre
n
tl
y
,
sh
e
is
p
u
rsu
in
g
a
M
a
ste
r
o
f
S
c
ien
c
e
in
Da
ta
S
c
ien
c
e
a
n
d
A
n
a
l
y
ti
c
s
a
t
Un
iv
e
rsiti
S
a
in
s
M
a
lay
sia
.
He
r
re
se
a
r
c
h
in
tere
sts
in
c
lu
d
e
b
ig
d
a
ta
re
se
a
rc
h
a
n
d
a
n
a
ly
ti
c
s,
p
o
w
e
r
b
u
sin
e
ss
a
n
a
l
y
ti
c
s,
a
n
d
m
a
c
h
in
e
lea
rn
in
g
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
m
in
g
y
in
g
h
a
n
4
6
9
5
8
@s
t
u
d
e
n
t.
u
sm
.
m
y
.
Az
m
a
n
A
b
M
a
li
k
re
c
e
iv
e
d
h
is
Dip
lo
m
a
in
El
e
c
tro
n
ic
T
e
c
h
n
o
lo
g
y
f
ro
m
KK
T
M
P
a
sir
M
a
s
i
n
2
0
0
7
,
Ba
c
h
e
l
o
r
in
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
a
n
d
T
e
c
h
n
o
l
o
g
y
f
ro
m
UN
IK
L
BM
I,
M
a
ste
r
in
El
e
c
tri
c
a
l
a
n
d
El
e
c
tro
n
i
c
En
g
in
e
e
rin
g
f
ro
m
USM
a
n
d
P
h
.
D.
in
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
f
ro
m
UI
T
M
.
His
in
tere
s
t
in
in
n
o
v
a
ti
o
n
t
o
w
a
rd
s
e
lec
tri
c
a
l
a
n
d
e
lec
tro
n
ic
a
n
d
c
ro
ss
m
u
lt
i
-
d
isc
ip
li
n
a
ry
a
re
a
s
to
id
e
n
ti
fy
a
n
e
w
m
o
d
e
l
o
r
m
e
th
o
d
i
n
e
n
g
in
e
e
rin
g
.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
d
e
lec
tri
c
a
l
p
o
w
e
r,
p
o
we
r
s
y
ste
m
,
r
e
n
e
w
a
b
le
e
n
e
rg
y
,
a
n
d
e
n
e
rg
y
sto
ra
g
e
.
He
is
c
u
rre
n
tl
y
a
S
e
n
io
r
L
e
c
tu
re
r
in
S
c
h
o
o
l
o
f
Co
m
p
u
ter
S
c
ien
c
e
,
Un
iv
e
rsiti
S
a
in
s
M
a
lay
sia
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
z
m
a
n
.
a
b
d
u
l@u
sm
.
m
y
.
No
o
r
m
a
d
i
n
a
h
Alli
a
s
re
c
e
iv
e
d
h
e
r
Ba
c
h
e
lo
r
o
f
En
g
in
e
e
rin
g
T
e
c
h
n
o
lo
g
y
(Ho
n
s)
in
Ne
tw
o
rk
in
g
S
y
ste
m
s
f
ro
m
Un
iv
e
rsit
y
Ku
a
la
L
u
m
p
u
r
-
M
a
la
y
si
a
n
In
stit
u
te
o
f
In
f
o
r
m
a
ti
o
n
T
e
c
h
n
o
lo
g
y
(Un
iK
L
-
M
IIT
)
in
2
0
0
8
.
S
h
e
o
b
tain
e
d
h
e
r
M
a
ste
r
a
n
d
P
h
.
D.
o
f
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
y
f
ro
m
th
e
sa
m
e
in
sti
tu
ti
o
n
(U
n
iKL
-
M
IIT
)
in
2
0
1
5
a
n
d
2
0
2
4
re
sp
e
c
ti
v
e
l
y
.
Cu
rre
n
tl
y
,
sh
e
se
r
v
e
s
a
s
a
S
e
n
io
r
L
e
c
tu
re
r
a
t
th
e
S
c
h
o
o
l
o
f
Co
m
p
u
ti
n
g
S
c
ien
c
e
s,
Co
ll
e
g
e
o
f
Co
m
p
u
ti
n
g
,
I
n
f
o
rm
a
ti
c
s
a
n
d
M
a
th
e
m
a
ti
c
s,
Un
iv
e
rsiti
T
e
k
n
o
lo
g
i
M
A
R
A
,
4
0
4
5
0
S
h
a
h
A
lam
,
S
e
lan
g
o
r,
M
a
lay
sia
.
He
r
re
se
a
r
c
h
in
tere
sts
in
c
lu
d
e
n
e
x
t
g
e
n
e
ra
ti
o
n
n
e
tw
o
rk
,
c
y
b
e
rse
c
u
rit
y
,
d
a
ta
a
n
a
ly
ti
c
s,
a
n
d
m
a
c
h
in
e
lea
rn
in
g
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
n
o
o
rm
a
d
in
a
h
0
9
@s
.
u
n
ik
l.
e
d
u
.
m
y
.
Ir
n
i
H
a
m
i
z
a
H
a
m
z
a
h
wa
s
b
o
rn
i
n
M
a
c
h
a
n
g
,
Ke
lan
tan
o
n
6
t
h
De
c
e
m
b
e
r
1
9
7
4
.
S
h
e
o
b
tai
n
e
d
h
e
r
B.
En
g
(H
o
n
s)
in
El
e
c
tri
c
a
l
a
n
d
El
e
c
tro
n
ic
En
g
in
e
e
rin
g
i
n
1
9
9
8
,
M
S
c
.
El
e
c
tro
n
ics
S
y
ste
m
a
n
d
De
sig
n
En
g
in
e
e
rin
g
in
2
0
0
5
a
n
d
P
h
.
D
.
in
Bio
M
EM
s
S
e
n
so
rs
i
n
2
0
1
3
,
w
h
ich
a
ll
h
a
d
b
e
e
n
o
b
tain
e
d
fro
m
S
c
h
o
o
l
o
f
o
f
El
e
c
tri
c
a
l
a
n
d
El
e
c
tro
n
ic
En
g
in
e
e
rin
g
,
Un
iv
e
rsiti
S
a
in
s
M
a
lay
sia
,
M
a
la
y
sia
.
S
h
e
is
c
u
rre
n
tl
y
a
S
e
n
i
o
r
L
e
c
tu
re
r
in
El
e
c
tro
n
ic
En
g
in
e
e
rin
g
De
p
a
rtm
e
n
t,
F
a
c
u
l
t
y
o
f
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
,
U
n
iv
e
rsiti
T
e
k
n
o
lo
g
i
M
A
RA
,
P
e
n
a
n
g
Bra
n
c
h
Ca
m
p
u
s,
M
a
lay
sia
.
He
r
re
se
a
rc
h
in
t
e
re
sts
in
c
l
u
d
e
b
io
se
n
s
o
rs,
Bi
o
M
EM
s,
n
e
u
ra
l
n
e
tw
o
rk
s,
a
n
d
re
n
e
w
a
b
le e
n
e
rg
y
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
irn
i
h
a
m
i@u
it
m
.
e
d
u
.
m
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.